© 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. 45779
    Prev
    Next
    INDEX
    Explanations

    Initially; continues; generates

    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
    ,*/}*.
    0.44
    CycleOffset
    0.44
     συγκεκρι
    0.43
    使其
    0.43
    ϊ
    0.43
     সদস্যদের
    0.42
    恳
    0.42
    ⊆
    0.42
    эм
    0.40
    出一个
    0.40
    POSITIVE LOGITS
     direction
    0.46
     aftermath
    0.43
    ந்தி
    0.43
     He
    0.43
     place
    0.42
     relation
    0.42
     Tujuan
    0.42
    the
    0.42
     Brahman
    0.41
     both
    0.41
    Activations Density 0.014%

    No Known Activations