© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5283
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE constraint keywords

    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_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
    DIALOG
    0.74
    hese
    0.72
    箅
    0.72
    sob
    0.70
    lysninger
    0.70
    Envelope
    0.70
    鼍
    0.69
     Among
    0.68
    爻
    0.68
    QueryResult
    0.68
    POSITIVE LOGITS
     default
    0.70
     PRIMARY
    0.69
     mandatory
    0.67
     infinite
    0.66
    默认
    0.65
     طبي
    0.64
     primaria
    0.64
    eliac
    0.64
     longitudinal
    0.63
     লেখক
    0.62
    Activations Density 0.124%

    No Known Activations