© 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. 201757
    Prev
    Next
    INDEX
    Explanations

    always round

    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
     States
    0.45
    furt
    0.43
    ad
    0.42
     Tactics
    0.41
     (
    0.41
     tactics
    0.40
     Contin
    0.39
    ائم
    0.39
    art
    0.38
     Yankees
    0.38
    POSITIVE LOGITS
    માં
    0.54
    WordInterval
    0.54
     کھول
    0.52
     və
    0.51
    ०
    0.50
     არის
    0.50
     एक्सप्ले
    0.50
    ेट्टी
    0.49
     మరియు
    0.48
     tyrannical
    0.48
    Activations Density 0.003%

    No Known Activations