© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236975
    Prev
    Next
    INDEX
    Explanations

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lanjut
    0.44
     attempt
    0.41
     into
    0.40
    abil
    0.40
    ิล
    0.40
    到
    0.39
     videom
    0.39
    ཧ
    0.38
     kuat
    0.38
    尝试
    0.38
    POSITIVE LOGITS
     высоте
    0.48
     maladie
    0.47
    тике
    0.47
    ті
    0.46
     புகை
    0.45
    чью
    0.44
     complej
    0.44
    preuve
    0.44
     среде
    0.43
    猬
    0.43
    Activations Density 0.002%

    No Known Activations