© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    for your

    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
     flanks
    0.82
     `${
    0.80
     चाहर
    0.78
     şunu
    0.77
    cendo
    0.76
    ্বল
    0.74
    bearer
    0.73
     sphinct
    0.73
    presentable
    0.72
     clienti
    0.71
    POSITIVE LOGITS
    在大
    0.88
     ص
    0.82
    вина
    0.81
     क्रांति
    0.80
     сча
    0.78
    始まり
    0.78
     ме
    0.77
    メタ
    0.76
     Mex
    0.76
    தியே
    0.75
    Activations Density 0.021%

    No Known Activations