© 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. 108026
    Prev
    Next
    INDEX
    Explanations

    advice or instructions

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

    This neuron fires on personal pronouns (e.g. “мне,” “Вам,” “me,” “ему”)—tokens referring to the speaker or addressee.

    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
     đón
    -0.84
     avven
    -0.78
    Merkmale
    -0.75
    𝔩
    -0.74
    Invariant
    -0.73
     tectonic
    -0.73
     folgenden
    -0.72
     请求
    -0.71
    ground
    -0.70
    方形
    -0.70
    POSITIVE LOGITS
     seems
    0.92
     жив
    0.89
     tick
    0.84
     siker
    0.80
     السود
    0.80
     becomes
    0.79
    мони
    0.75
    %)
    0.74
    ("</
    0.73
     seemed
    0.72
    Activations Density 0.012%

    No Known Activations