© 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. 124683
    Prev
    Next
    INDEX
    Explanations

    revenge puts station creator cheese

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

    financial markets, genuine interest, multiple audits

    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
     ip
    0.48
     png
    0.47
     gast
    0.47
     v
    0.46
     per
    0.46
     Mainz
    0.45
     Panoramic
    0.45
     fün
    0.45
     to
    0.44
     shirt
    0.44
    POSITIVE LOGITS
    ਜ਼
    0.51
    silyl
    0.50
    culis
    0.50
    cX
    0.48
    卒
    0.47
    がございます
    0.47
    CQL
    0.47
    ੱਸ
    0.46
    SRPI
    0.46
    可能です
    0.46
    Activations Density 0.001%

    No Known Activations