© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    escaping special characters

    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
    /
    1.30
     ciertas
    1.10
    詳しくは
    1.09
     veya
    1.00
     &/
    1.00
     või
    1.00
     vostra
    0.99
    ubahan
    0.98
     /
    0.97
     atau
    0.97
    POSITIVE LOGITS
     свой
    2.05
     свое
    1.82
     splendor
    1.77
     своего
    1.74
    صل
    1.71
     Itu
    1.71
     свою
    1.70
     Pad
    1.70
     Sos
    1.68
     tok
    1.68
    Activations Density 0.013%

    No Known Activations