© 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. 158864
    Prev
    Next
    INDEX
    Explanations

    Leverkusen, coupe, grave, continuum

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

    spreadsheet formula application

    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
    NUMBER
    0.49
    ب
    0.46
     चुक
    0.46
    कांत
    0.45
    кон
    0.45
    약을
    0.45
    黄
    0.44
    드
    0.43
     संपूर्ण
    0.43
    মূল
    0.42
    POSITIVE LOGITS
     wana
    0.50
    itabbo
    0.50
     與
    0.50
     basilaires
    0.48
     LPTMR
    0.46
     場
    0.44
     Moreover
    0.44
     econometric
    0.44
     Raised
    0.44
     APIDC
    0.44
    Activations Density 0.001%

    No Known Activations