© 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. 91294
    Prev
    Next
    INDEX
    Explanations

    payment with PayPal

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

    columns and data

    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
    ୍ର
    0.48
    كثر
    0.45
    ନ
    0.44
     necesitamos
    0.42
    の内
    0.42
    এসসি
    0.42
    ল
    0.42
    립니다
    0.41
    র
    0.40
     sót
    0.40
    POSITIVE LOGITS
     麻
    0.51
     twinning
    0.46
     BAL
    0.46
     אַ
    0.46
     Farah
    0.46
     黃
    0.45
     instal
    0.45
     FLA
    0.45
     JANUARY
    0.44
     UIS
    0.44
    Activations Density 0.000%

    No Known Activations