© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10039
    Prev
    Next
    INDEX
    Explanations

    isset condition checks

    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_9_width_262k_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
    സ
    1.94
    های
    1.85
     mathematically
    1.76
     Increased
    1.67
    getAvg
    1.65
     Increasing
    1.63
    उड
    1.63
    த்து
    1.59
     борьбе
    1.59
     Establishing
    1.59
    POSITIVE LOGITS
    in
    2.88
    te
    2.84
    le
    2.72
    c
    2.69
    ten
    2.59
    tt
    2.58
    ی
    2.50
    as
    2.48
    ted
    2.37
    ting
    2.31
    Activations Density 0.000%

    No Known Activations