© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14062
    Prev
    Next
    INDEX
    Explanations

    without explicit labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    <unused2037>
    0.98
     zeg
    0.94
     हैज
    0.93
     SIP
    0.93
     saldır
    0.91
     perimeter
    0.90
    Arg
    0.90
    Exp
    0.90
     urgently
    0.90
    <unused447>
    0.89
    POSITIVE LOGITS
    given
    1.00
     given
    0.93
    ?).
    0.88
    精彩
    0.85
    inology
    0.83
     அதே
    0.77
     Completion
    0.76
     definite
    0.76
     anything
    0.75
     mẽ
    0.75
    Activations Density 0.003%

    No Known Activations