© 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. 68372
    Prev
    Next
    INDEX
    Explanations

    substantial experience

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

    entity, Majority Stake, or forgetting

    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
     postaci
    0.49
     idols
    0.48
     pią
    0.45
     있는
    0.45
    艺
    0.44
    一个
    0.44
    Pref
    0.44
     instalaciones
    0.44
     templo
    0.43
    רוי
    0.43
    POSITIVE LOGITS
    automated
    0.51
     कंप्र
    0.45
    otroph
    0.45
     Faster
    0.44
    垪
    0.44
    obtained
    0.44
    óis
    0.44
    大多數
    0.44
    出自
    0.44
    ố
    0.44
    Activations Density 0.001%

    No Known Activations