© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13232
    Prev
    Next
    INDEX
    Explanations

    as a, i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     ​​
    0.89
    한
    0.77
     Ren
    0.75
    चा
    0.71
     ​​​​
    0.71
    lerin
    0.70
     berg
    0.70
    ները
    0.70
    레
    0.70
     nanny
    0.69
    POSITIVE LOGITS
    thickness
    1.00
     đau
    0.93
    ாய்ச்ச
    0.90
     descriptor
    0.83
    Código
    0.82
    Measure
    0.80
     toca
    0.79
     measure
    0.79
    我有
    0.79
    respuesta
    0.78
    Activations Density 0.157%

    No Known Activations