© 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-65K
    7. 65133
    Prev
    Next
    INDEX
    Explanations

    physical address or palindrome insertion

    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_65k_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
    」
    0.44
     for
    0.40
    ')
    0.40
     Tonight
    0.39
     flipped
    0.38
     placebo
    0.38
     speculative
    0.38
     massive
    0.37
     QQ
    0.37
    "
    0.37
    POSITIVE LOGITS
    Hierarchy
    0.49
    isert
    0.49
     Drapeau
    0.48
    દાર
    0.47
    醎
    0.47
    鐩
    0.46
    인이
    0.46
    ೆಯ
    0.45
    Mât
    0.45
    ądź
    0.45
    Activations Density 0.017%

    No Known Activations