© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71859
    Prev
    Next
    INDEX
    Explanations

    vulnerable, unanswered, early

    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
     ငါ
    0.46
    の内
    0.44
    ։
    0.43
     bleu
    0.43
     കാണ
    0.41
     Freude
    0.41
    ))))
    0.41
     logiciel
    0.41
    性は
    0.41
     gpointer
    0.40
    POSITIVE LOGITS
     airtight
    0.46
     VPD
    0.46
     revolutions
    0.44
     roadblocks
    0.44
     a
    0.43
    moveTo
    0.43
     हिमा
    0.42
     moveTo
    0.42
    calcul
    0.41
    牖
    0.41
    Activations Density 0.002%

    No Known Activations