© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30592
    Prev
    Next
    INDEX
    Explanations

    Western Digital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coasts
    0.42
    кість
    0.41
     coast
    0.39
    coast
    0.39
    ုန်း
    0.38
     сторону
    0.37
    駕
    0.37
    }^{-}\
    0.37
    ಪ್ಪು
    0.37
    贸
    0.37
    POSITIVE LOGITS
    ized
    0.52
     mucho
    0.45
    izable
    0.44
     Philharmonic
    0.43
    hdu
    0.42
    clarinet
    0.41
     ejaculation
    0.41
    IZATION
    0.40
    椹
    0.40
    ız
    0.39
    Activations Density 0.002%

    No Known Activations