© 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. 136
    Prev
    Next
    INDEX
    Explanations

    punctuation and conversational markers

    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
    tAux
    0.37
    เวณ
    0.36
    грева
    0.36
    Ꮏ
    0.35
     '**
    0.35
    牲
    0.34
     ので
    0.34
    囉
    0.33
    toLocale
    0.32
    市区
    0.32
    POSITIVE LOGITS
     dont
    0.41
    dont
    0.39
    git
    0.36
     Sam
    0.36
     unmodified
    0.36
     nonstop
    0.36
    ns
    0.35
    耑
    0.35
     Italia
    0.34
     sec
    0.33
    Activations Density 0.048%

    No Known Activations