© 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. 136203
    Prev
    Next
    INDEX
    Explanations

    boolean data type or step function

    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
     Corsair
    0.49
    なかなか
    0.47
    क्षि
    0.44
     lleg
    0.44
     mezcla
    0.43
    长大
    0.43
    攻撃
    0.42
    贼
    0.42
    ехала
    0.42
     jugó
    0.41
    POSITIVE LOGITS
    utors
    0.47
     safeguarding
    0.45
     বৈ
    0.44
    achsen
    0.44
     entscheiden
    0.43
    etary
    0.41
    ettore
    0.41
    enen
    0.41
     climate
    0.40
     climatic
    0.40
    Activations Density 0.006%

    No Known Activations