© 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-16K
    7. 1175
    Prev
    Next
    INDEX
    Explanations

    back, background, matadors, lubricant, 床前

    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_16k_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
     NHE
    0.81
    Eugene
    0.72
     Roz
    0.70
     canes
    0.70
     Categor
    0.69
     Pati
    0.69
     mèo
    0.69
    낍
    0.67
     cutters
    0.67
     Cutter
    0.67
    POSITIVE LOGITS
     Back
    1.64
    Back
    1.63
     back
    1.56
    back
    1.56
     BACK
    1.46
    BACK
    1.43
    バック
    1.39
     الخلف
    1.36
    Behind
    1.33
    backing
    1.30
    Activations Density 1.231%

    No Known Activations