© 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-262K
    7. 47118
    Prev
    Next
    INDEX
    Explanations

    specific topics and contexts

    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_262k_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
    probabilities
    0.47
    д
    0.47
    віт
    0.45
    әм
    0.45
    \%,
    0.44
    ancji
    0.44
    効率
    0.44
    計画
    0.44
    quetas
    0.43
    信する
    0.43
    POSITIVE LOGITS
     dir
    0.47
    过
    0.46
     tante
    0.45
     își
    0.44
     precedent
    0.44
     tu
    0.43
     aik
    0.43
     tm
    0.42
    直送
    0.42
     kautta
    0.41
    Activations Density 0.001%

    No Known Activations