© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37962
    Prev
    Next
    INDEX
    Explanations

    letter of recommendation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on passages listing or talking about potential referees or reference‐providers (e.g. names of people who can give letters of recommendation) in an application context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lamo
    -0.87
     poë
    -0.84
     disassembly
    -0.80
     grise
    -0.77
     ulang
    -0.76
     dismant
    -0.76
     schéma
    -0.76
     beverly
    -0.75
    diva
    -0.74
     moderators
    -0.73
    POSITIVE LOGITS
     letters
    2.86
     recommendation
    2.73
     letter
    2.33
     recommendations
    2.20
     recommend
    2.19
     Recommendation
    2.09
     Letters
    2.05
    letters
    2.00
    Recommendation
    1.97
    recommendation
    1.86
    Activations Density 0.017%

    No Known Activations