© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1481
    Prev
    Next
    INDEX
    Explanations

    protocol, format, type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    s
    1.56
    ной
    1.10
    ời
    1.09
    in
    1.09
    at
    1.01
    time
    1.01
    il
    1.00
    AGE
    1.00
    pod
    0.99
    лів
    0.99
    POSITIVE LOGITS
    ли
    1.27
    ي
    1.20
     Pics
    1.18
     setbacks
    1.16
     underpin
    1.16
     carbides
    1.14
     nieces
    1.12
    ન
    1.12
     radiographs
    1.10
     angle
    1.09
    Activations Density 0.491%

    No Known Activations