© 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. 40-GEMMASCOPE-2-RES-262K
    4. 165216
    Prev
    Next
    INDEX
    Explanations

    conditions, degree, float

    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
    トマト
    0.44
    ቲ
    0.39
    দেশ
    0.38
    Thomas
    0.38
    Lamp
    0.37
    ‥
    0.37
    ሮች
    0.36
    ます
    0.36
    দ্ব
    0.36
    ␶
    0.36
    POSITIVE LOGITS
     tribune
    0.39
     forum
    0.39
    ín
    0.38
    him
    0.38
    ניין
    0.38
    ILLE
    0.37
    âtre
    0.37
    放到
    0.37
    ற்கான
    0.36
    itimate
    0.36
    Activations Density 0.000%

    No Known Activations