© 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. 25316
    Prev
    Next
    INDEX
    Explanations

    email, learned, connection, spoke, yelling

    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
    v
    0.41
     Craven
    0.40
     lakes
    0.39
    很难
    0.39
     ফসল
    0.39
     correctement
    0.39
    STATS
    0.38
     frutto
    0.38
     mower
    0.38
     skill
    0.38
    POSITIVE LOGITS
     strikingly
    0.47
     otherworldly
    0.45
     zahrani
    0.44
    </h1>
    0.44
    際は
    0.42
    Когда
    0.42
    ersonal
    0.42
    Celebrate
    0.42
    ফতার
    0.41
     unmist
    0.41
    Activations Density 0.002%

    No Known Activations