© 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. 143555
    Prev
    Next
    INDEX
    Explanations

    Matthew usage

    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
     uncond
    0.45
    雒
    0.41
    ampunk
    0.39
     molle
    0.38
    ccionar
    0.38
     grilled
    0.37
     relayed
    0.37
    ര്‍ട്ട്
    0.37
    heda
    0.36
    🚃
    0.36
    POSITIVE LOGITS
    破坏
    0.39
     విజ
    0.39
    Б
    0.39
     cancerous
    0.38
    ฑ
    0.38
    Ἠ
    0.38
    Throw
    0.38
    trash
    0.38
     Goto
    0.37
     Topics
    0.37
    Activations Density 0.048%

    No Known Activations