© 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. 160611
    Prev
    Next
    INDEX
    Explanations

    squash fanatic, pray for, क्या बात है

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

    asset tokenizationfish farming

    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
    드가
    0.53
    ENDING
    0.51
    “
    0.49
    "!
    0.48
    
    0.48
    드의
    0.48
    ї
    0.48
    "...
    0.48
    ﺍ
    0.48
    \">
    0.47
    POSITIVE LOGITS
     Giorgio
    0.47
     Virgin
    0.47
     shareholders
    0.47
     Rio
    0.45
     Alto
    0.45
     Ríos
    0.45
     Rios
    0.44
     pledge
    0.44
     Patel
    0.43
     Pavel
    0.43
    Activations Density 0.000%

    No Known Activations