© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162152
    Prev
    Next
    INDEX
    Explanations

    hermit, hermès, hermitage

    np_acts-logits-general · gemini-2.5-flash-lite

    placed mushrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ")
    0.55
    d
    0.54
    ratings
    0.50
    "'
    0.47
    aline
    0.47
    had
    0.46
    FOR
    0.46
    rect
    0.46
    Moss
    0.46
    st
    0.46
    POSITIVE LOGITS
    તા
    0.48
     filthy
    0.47
     intestate
    0.47
     grungy
    0.47
    та
    0.46
    оти
    0.46
    𝒏
    0.45
    urnama
    0.44
    νε
    0.44
    وتا
    0.44
    Activations Density 0.001%

    No Known Activations