© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191428
    Prev
    Next
    INDEX
    Explanations

    word class delimiters

    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_40_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
    ళ్ల
    0.41
    block
    0.40
     keras
    0.39
     parasitic
    0.38
     closet
    0.38
    亢
    0.37
     blockchain
    0.35
     nascent
    0.35
     Fletcher
    0.35
     split
    0.35
    POSITIVE LOGITS
     Zusammenarbeit
    0.42
    妽
    0.38
    patan
    0.37
     Ду
    0.36
    堤
    0.36
    פה
    0.36
    âche
    0.36
    डले
    0.36
     Collaboration
    0.35
    互動
    0.35
    Activations Density 0.001%

    No Known Activations