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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1563
    Prev
    Next
    INDEX
    Explanations

    formal salutations and sender information

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

    The neuron predominantly fires on long sequences of digits and related punctuation in document headers, such as docket or reference numbers.

    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
    --}}
    -0.90
    uminum
    -0.82
    )}.
    -0.81
    ḳ
    -0.79
     chica
    -0.79
     PROCESSES
    -0.79
    idp
    -0.78
    ∷
    -0.77
    =[[
    -0.76
     DIRECTIONS
    -0.75
    POSITIVE LOGITS
    Dear
    1.32
     Mr
    1.15
     Dear
    1.14
     VIA
    1.12
     Via
    1.06
     Ms
    1.05
    Via
    1.02
    Mr
    1.00
     dear
    0.98
    Attention
    0.92
    Activations Density 0.229%

    No Known Activations