© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98839
    Prev
    Next
    INDEX
    Explanations

    google groups

    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_40_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
    atsii
    0.44
    ienia
    0.40
     ભારત
    0.40
     ಬ
    0.40
    ❮
    0.40
    blogspot
    0.39
     गर्ल्स
    0.39
     कुटु
    0.39
     बला
    0.38
    jén
    0.38
    POSITIVE LOGITS
    groups
    0.38
     labyr
    0.38
     groups
    0.38
    files
    0.37
     packets
    0.37
    㓦
    0.37
     folds
    0.37
    eps
    0.37
     Files
    0.37
     provisioning
    0.36
    Activations Density 0.002%

    No Known Activations