© 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. 52189
    Prev
    Next
    INDEX
    Explanations

    review Arabic Signature insane depicted

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

    activities associated with boys

    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
    шивания
    0.47
    შირ
    0.45
    preds
    0.45
    ícios
    0.44
    ânia
    0.44
    uju
    0.44
    ખ્યા
    0.43
    ἆ
    0.43
    ási
    0.43
    땔
    0.43
    POSITIVE LOGITS
    ONENT
    0.58
     invern
    0.51
    TERMIN
    0.50
     voort
    0.48
     feb
    0.48
     hunk
    0.48
     domine
    0.47
     ու
    0.46
    handsome
    0.46
    geke
    0.46
    Activations Density 0.000%

    No Known Activations