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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28628
    Prev
    Next
    INDEX
    Explanations

    sum of numbers

    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
    自从
    0.43
     approximately
    0.41
     gafas
    0.41
     generan
    0.40
     세
    0.40
     circa
    0.39
    大约
    0.38
     costs
    0.38
     mínima
    0.38
    ća
    0.37
    POSITIVE LOGITS
    TrackAngle
    0.39
    깽
    0.38
    MODKEY
    0.37
    ელს
    0.37
    攵
    0.37
    ulli
    0.36
    ），
    0.36
    pulsewidth
    0.35
    brecht
    0.35
    otard
    0.35
    Activations Density 0.008%

    No Known Activations