© 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. 117105
    Prev
    Next
    INDEX
    Explanations

    profile, life, involved, vertical

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

    Breakdown and check components

    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
     bude
    0.48
    keye
    0.46
     سيكون
    0.46
    па
    0.45
    кого
    0.45
     стане
    0.45
    |_{\
    0.45
     conviene
    0.45
    ዃ
    0.45
    place
    0.44
    POSITIVE LOGITS
    re
    0.57
    ree
    0.51
     NaN
    0.46
     Nationalism
    0.45
     کف
    0.45
     grud
    0.43
    观点
    0.41
     רי
    0.41
     jav
    0.41
     edizione
    0.41
    Activations Density 0.001%

    No Known Activations