© 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. 31091
    Prev
    Next
    INDEX
    Explanations

    arranged times

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

    key followed by prepositions

    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
     سیستم
    0.51
     დიდი
    0.49
    nagyobb
    0.48
     रिमाइंडर
    0.47
    ன்
    0.47
     கலங்கரை
    0.46
     یار
    0.46
     ジ
    0.45
     recensement
    0.45
     सोबत
    0.44
    POSITIVE LOGITS
     determinadas
    0.40
    щать
    0.40
    ／
    0.39
    /**',
    0.38
     intrepid
    0.38
     Martín
    0.37
    ((
    0.37
     offenders
    0.37
     In
    0.37
    슈
    0.37
    Activations Density 0.000%

    No Known Activations