© 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. 5997
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
    6
    0.50
    0.49
    3
    0.49
    7
    0.46
     actuated
    0.44
    9
    0.43
     \|
    0.42
     condoms
    0.42
     alken
    0.42
     syringes
    0.42
    POSITIVE LOGITS
    '
    0.71
    ’
    0.50
    то
    0.45
    ל
    0.45
    elbe
    0.44
    ने
    0.44
    жи
    0.43
    ك
    0.43
    ியின்
    0.41
    el
    0.41
    Activations Density 0.411%

    No Known Activations