© 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. 43540
    Prev
    Next
    INDEX
    Explanations

    fleshy part

    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
    targeted
    0.46
    🌛
    0.44
    dataFormat
    0.43
    ！)
    0.43
    parsedBlock
    0.42
     speeches
    0.41
    শোধ
    0.41
    😶
    0.40
    tional
    0.40
    scenes
    0.39
    POSITIVE LOGITS
     to
    0.45
     in
    0.45
     les
    0.44
     employers
    0.43
     licensed
    0.43
     Workers
    0.43
     employed
    0.43
     misinformation
    0.43
     landlords
    0.42
     rę
    0.42
    Activations Density 0.008%

    No Known Activations