© 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. 169656
    Prev
    Next
    INDEX
    Explanations

    use the

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

    approach is

    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
    ANTED
    0.50
     پھ
    0.49
    *,
    0.47
    <0x00>
    0.45
     δύο
    0.45
     τρί
    0.45
     strutt
    0.44
     troisième
    0.44
    ,"+
    0.44
     respectively
    0.43
    POSITIVE LOGITS
     இதன
    0.48
    願意
    0.46
    bells
    0.45
     notions
    0.45
    ilya
    0.45
    utam
    0.44
    पणे
    0.44
     shopping
    0.44
    ராம
    0.44
     ordination
    0.43
    Activations Density 0.000%

    No Known Activations