© 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. 41090
    Prev
    Next
    INDEX
    Explanations

    parenthesized lists and quotes

    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
    mets
    0.52
    t
    0.52
    et
    0.49
    o
    0.49
    epub
    0.49
    as
    0.48
    eel
    0.48
    shell
    0.48
    gets
    0.46
    mat
    0.46
    POSITIVE LOGITS
     każdy
    0.46
     বরা
    0.44
     @_
    0.43
     testify
    0.43
    aryana
    0.42
     JOUR
    0.42
    姦
    0.42
    に近い
    0.41
     Humanitarian
    0.41
    死的
    0.41
    Activations Density 0.001%

    No Known Activations