© 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-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    identifies custom interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ágina
    1.48
    援
    1.45
    欖
    1.44
    jš
    1.42
    棂
    1.41
     kèo
    1.41
    獻
    1.39
    cluso
    1.39
    angi
    1.38
    擒
    1.37
    POSITIVE LOGITS
    Liqu
    1.22
    وارد
    1.22
    properties
    1.20
     gravitation
    1.20
    e
    1.19
    o
    1.19
    RENGTH
    1.15
    ाब
    1.13
     bip
    1.13
     reject
    1.13
    Activations Density 0.056%

    No Known Activations