© 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. 203887
    Prev
    Next
    INDEX
    Explanations

    specifications and conditions

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

    lists numbers and items

    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
    జి
    0.48
    Hướng
    0.46
    ăţ
    0.45
    淫
    0.44
    órm
    0.44
    怂
    0.44
     Ariel
    0.43
     způsob
    0.43
    ၇
    0.43
    ଟି
    0.43
    POSITIVE LOGITS
    otherwise
    0.49
    DOUT
    0.46
     работал
    0.46
    adze
    0.46
    pressed
    0.45
    ="{{
    0.45
    اپ
    0.44
     сталки
    0.44
     binding
    0.44
     marcas
    0.44
    Activations Density 0.000%

    No Known Activations