© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105066
    Prev
    Next
    INDEX
    Explanations

    rate statement

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

    body descriptions and characters

    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
     Batter
    0.45
    ’
    0.45
     Pipe
    0.44
     Vocational
    0.43
     Detox
    0.43
     छोटा
    0.43
    orro
    0.43
     Polytechnic
    0.43
     फ्ला
    0.42
     Ecological
    0.42
    POSITIVE LOGITS
    銀行
    0.45
    槇
    0.44
    ARCHIVO
    0.44
    ?")
    0.43
    নির্ব
    0.43
    ِل
    0.42
     vět
    0.42
     ଚ
    0.42
     କ
    0.41
    顧客
    0.40
    Activations Density 0.003%

    No Known Activations