© 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. 238894
    Prev
    Next
    INDEX
    Explanations

    kms, hrs, distance

    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
     gebracht
    0.43
     acusado
    0.43
     &/
    0.42
    aknya
    0.40
    KURZBESCHREIBUNG
    0.40
    SDLCheck
    0.40
     mistrust
    0.40
    حث
    0.40
     inklusive
    0.40
     adjudged
    0.39
    POSITIVE LOGITS
    蓼
    0.50
     ecosystems
    0.49
    胶
    0.47
    arán
    0.46
    ラ
    0.46
    𝓵
    0.46
     మీడి
    0.45
    NaClO
    0.43
    т
    0.43
    ាប
    0.43
    Activations Density 0.001%

    No Known Activations