© 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. 87536
    Prev
    Next
    INDEX
    Explanations

    overrepresentation, strong antenna, private programs

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

    standardizing text values

    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
    rę
    0.57
    entlichen
    0.49
     ഉ
    0.48
    eke
    0.48
     условии
    0.46
     நேரத்தில்
    0.46
     시간에
    0.46
    Ỉ
    0.46
     einzelnen
    0.45
    emois
    0.45
    POSITIVE LOGITS
    חר
    0.49
    一片
    0.49
    blueprint
    0.47
     Tactical
    0.45
    posts
    0.45
     marcha
    0.44
    டிய
    0.44
    union
    0.43
    بغ
    0.43
     Forum
    0.43
    Activations Density 0.000%

    No Known Activations