© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128198
    Prev
    Next
    INDEX
    Explanations

    fan conduct violations

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

    punctuation and common words like by, cut, reminder

    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
     nervioso
    0.48
     è
    0.46
     Terminator
    0.43
     są
    0.43
     esté
    0.43
     ज्यादा
    0.43
     começa
    0.43
    是
    0.43
     довольно
    0.42
     denke
    0.42
    POSITIVE LOGITS
     профилакти
    0.43
    Fluid
    0.42
     solvation
    0.41
     recue
    0.41
    гази
    0.40
     પરિ
    0.40
    ходила
    0.40
    Sheila
    0.39
    ச்சே
    0.39
     silam
    0.39
    Activations Density 0.001%

    No Known Activations