Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15055
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    2.16
     '
    2.11
     "'
    2.00
    '
    1.99
     "[
    1.75
     '"
    1.70
    '"
    1.70
     ''
    1.61
    "'
    1.61
    "[
    1.60
    POSITIVE LOGITS
     “‘
    2.39
    ’,
    2.31
    ,’”
    2.31
    ’”
    2.25
     ‘
    2.23
    ,’
    2.22
    .’”
    2.16
    ’.
    2.14
    ’)
    2.13
    ’.”
    2.11
    Activations Density 0.206%

    No Known Activations