© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    literal elimination

    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
     in
    0.41
     C
    0.41
    かもしれませんが
    0.40
    在
    0.39
     our
    0.39
    U
    0.38
     U
    0.38
    W
    0.38
     L
    0.38
     the
    0.37
    POSITIVE LOGITS
    ។
    0.67
    ։
    0.64
    。
    0.62
    ™.
    0.59
    。「
    0.56
    ሉ።
    0.55
    .¹
    0.53
    ।...
    0.52
    ။
    0.52
    ።
    0.51
    Activations Density 0.000%

    No Known Activations