© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4395
    Prev
    Next
    INDEX
    Explanations

    HTML tag closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     hoods
    1.55
    ^{(\
    1.33
    ﺌ
    1.29
    }^{(\
    1.27
    туру
    1.24
    рома
    1.23
    тары
    1.21
    ^{*}=\
    1.21
    敛
    1.21
    ванович
    1.20
    POSITIVE LOGITS
     Jimin
    1.79
     mesaj
    1.67
     Amber
    1.66
    Message
    1.63
     Cras
    1.62
     Elaine
    1.62
     Hailey
    1.60
     Hye
    1.59
     Britt
    1.56
     Indus
    1.55
    Activations Density 0.000%

    No Known Activations