© 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. 5919
    Prev
    Next
    INDEX
    Explanations

    matching, Kindness, Hours

    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
    tedir
    0.52
    ༸
    0.46
    います
    0.44
     накопи
    0.43
    𝘂
    0.43
    实在
    0.43
    modulo
    0.42
     modulo
    0.42
    tens
    0.42
    젝트
    0.42
    POSITIVE LOGITS
    }-$
    0.57
    (),"
    0.52
     ដើម្បី
    0.50
     Hours
    0.47
    }.$
    0.47
    Kalb
    0.45
     matching
    0.45
     Kindness
    0.44
    す
    0.44
     Matching
    0.43
    Activations Density 0.000%

    No Known Activations