© 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. 52740
    Prev
    Next
    INDEX
    Explanations

    tell me

    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
    u
    0.61
    id
    0.60
    db
    0.49
    email
    0.48
    ued
    0.47
     talks
    0.47
    า
    0.46
     offici
    0.46
    ues
    0.45
    utt
    0.45
    POSITIVE LOGITS
     intérieur
    0.52
    ユニ
    0.51
     উঠবে
    0.50
     உடை
    0.47
    綃
    0.46
     valeur
    0.46
    JUNE
    0.46
     그러면은
    0.46
    なら
    0.45
    治療
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.