© 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. 102550
    Prev
    Next
    INDEX
    Explanations

    recent collection

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

    legitimacy and niches

    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
    parents
    0.48
    deo
    0.47
    rico
    0.47
    G
    0.47
    group
    0.47
    regional
    0.46
    ini
    0.46
    cuando
    0.46
    4
    0.45
    rica
    0.44
    POSITIVE LOGITS
    ться
    0.48
    🫤
    0.48
     récent
    0.45
    Uninstall
    0.44
     mangas
    0.44
     récentes
    0.44
    年来
    0.44
     inactivity
    0.44
    段时间
    0.43
    并非
    0.42
    Activations Density 0.000%

    No Known Activations