© 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. 46154
    Prev
    Next
    INDEX
    Explanations

    writing genres or specific entities

    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
    u
    0.52
    }";
    0.46
    justify
    0.45
    oclaw
    0.42
    trivial
    0.42
    प्पल
    0.42
    }"),
    0.42
    ку
    0.42
    lø
    0.42
    ReturnValue
    0.41
    POSITIVE LOGITS
     Knight
    0.47
     Leonardo
    0.42
     Bewertung
    0.42
     রাখতে
    0.42
     інформа
    0.41
     bestimmten
    0.40
    knight
    0.40
    情報
    0.40
     Technische
    0.40
     известных
    0.40
    Activations Density 0.035%

    No Known Activations