© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 438
    Prev
    Next
    INDEX
    Explanations

    JSON punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    —
    1.01
    ,
    1.00
    -
    0.94
    ?
    0.92
    .
    0.91
    =
    0.84
     –
    0.83
    …
    0.82
    /
    0.81
     =
    0.77
    POSITIVE LOGITS
    Појединачна
    1.20
     ///<
    1.16
     andRow
    1.12
     tačiau
    1.12
     //!
    1.11
    omitempty
    1.08
     //=>
    1.08
     '-',
    1.08
     '-':
    1.07
    țională
    1.07
    Activations Density 0.084%

    No Known Activations