© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57243
    Prev
    Next
    INDEX
    Explanations

    words after specific terms

    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
    すぎる
    0.44
    and
    0.43
    盛
    0.42
    </h2>
    0.41
    PX
    0.40
    州市
    0.40
     pēc
    0.40
    行李
    0.40
    EndDate
    0.40
     worsen
    0.40
    POSITIVE LOGITS
     thermocou
    0.53
     coalgebras
    0.50
     protrusions
    0.49
     tég
    0.49
     numerals
    0.49
     tankers
    0.49
     objets
    0.48
     replicas
    0.48
     callers
    0.47
    渍
    0.47
    Activations Density 0.001%

    No Known Activations