© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11975
    Prev
    Next
    INDEX
    Explanations

    root directory paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hesis
    2.96
    υκ
    2.76
     चाहें
    2.69
     secondary
    2.68
    nem
    2.65
    渑
    2.58
    unum
    2.53
    renderer
    2.48
    శ్వ
    2.44
    primary
    2.44
    POSITIVE LOGITS
    […]
    2.94
    “”
    2.89
    ############
    2.78
    “
    2.74
    “[
    2.69
    हतक
    2.59
    mlich
    2.55
    ..”
    2.50
    #########
    2.49
    ।”
    2.45
    Activations Density 0.009%

    No Known Activations