© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19413
    Prev
    Next
    INDEX
    Explanations

    highlights advancing objectives

    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
     গ্রামে
    0.53
     ニュー
    0.51
     TNumber
    0.47
     insegn
    0.47
     учитель
    0.46
     apprend
    0.46
     tagReport
    0.46
    Ս
    0.46
     traduction
    0.45
     உருவா
    0.45
    POSITIVE LOGITS
     propellers
    0.44
    hstack
    0.42
     tapered
    0.41
     sightseeing
    0.40
     الاثنين
    0.40
    लीवुड
    0.40
    èbre
    0.40
    abilité
    0.38
     standstill
    0.38
    aphazard
    0.38
    Activations Density 0.006%

    No Known Activations