© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55526
    Prev
    Next
    INDEX
    Explanations

    breaking down lists and ideas

    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/layer_31_width_65k_l0_medium
    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
    <unused503>
    0.46
    бере
    0.45
     دقت
    0.45
     عندما
    0.44
     когато
    0.43
     encourages
    0.43
     rekord
    0.42
    .¹
    0.42
     لذا
    0.42
    sekten
    0.42
    POSITIVE LOGITS
    )
    0.51
     species
    0.46
     radii
    0.44
     belong
    0.44
    或其他
    0.43
     অথবা
    0.43
    তাহাদের
    0.43
    或
    0.43
    }
    0.42
    ’)
    0.42
    Activations Density 0.016%

    No Known Activations