© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58302
    Prev
    Next
    INDEX
    Explanations

    chartered specific language

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

    The neuron flags relatively rare or content‐heavy tokens (i.e. high–TFIDF words rather than common stop words).

    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
    хать
    -0.74
     school
    -0.72
    pfung
    -0.69
     gather
    -0.69
     Histórico
    -0.68
     física
    -0.65
    隷
    -0.65
     School
    -0.65
     findAll
    -0.64
     校
    -0.64
    POSITIVE LOGITS
    Joachim
    0.76
    ླ
    0.72
    ьа
    0.71
    regu
    0.71
     ayudarte
    0.71
     mendatang
    0.70
     trasladado
    0.70
    ridged
    0.69
     Росії
    0.69
    ਓ
    0.68
    Activations Density 0.046%

    No Known Activations