© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6354
    Prev
    Next
    INDEX
    Explanations

    strong performance

    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_22_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
     पेशेवरों
    0.74
    elective
    0.72
    හු
    0.71
    Ų
    0.70
     far
    0.68
    吸
    0.67
     വൈ
    0.66
     adquirido
    0.65
    Pick
    0.64
     axial
    0.64
    POSITIVE LOGITS
     discloses
    0.73
     Performance
    0.70
    Performance
    0.69
     Visibility
    0.67
     Residency
    0.64
    see
    0.64
     see
    0.63
    seeing
    0.62
    =":
    0.62
    nz
    0.61
    Activations Density 0.065%

    No Known Activations