© 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. 150266
    Prev
    Next
    INDEX
    Explanations

    taught grades or kindergarten

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

    current now multilingual

    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
    ତା
    0.52
    𝘇
    0.48
    Validate
    0.47
     успеш
    0.46
    ቐ
    0.45
    িনা
    0.44
     personalizada
    0.44
    стро
    0.44
    ି
    0.44
    礎
    0.44
    POSITIVE LOGITS
    ตอนนี้
    0.56
     nhưng
    0.52
    ற்போது
    0.50
     MGM
    0.47
    แต่
    0.45
     Panasonic
    0.45
     fluidity
    0.45
     Crem
    0.44
     maintenant
    0.44
     MCA
    0.43
    Activations Density 0.000%

    No Known Activations