© 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. 46795
    Prev
    Next
    INDEX
    Explanations

    units and abbreviations

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

    URLs and code identifiers

    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
    3
    0.90
    8
    0.86
    ون
    0.83
    4
    0.82
    5
    0.79
    7
    0.76
    2
    0.75
    9
    0.74
    6
    0.72
    or
    0.72
    POSITIVE LOGITS
    ።
    0.68
    ،
    0.65
     Ն
    0.64
    ؟
    0.63
    ։
    0.62
    ፣
    0.62
     extraordinaire
    0.61
     cliquer
    0.61
    །
    0.61
     bloqueo
    0.60
    Activations Density 0.063%

    No Known Activations