© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 538
    Prev
    Next
    INDEX
    Explanations

    how or why questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    ****************
    0.59
    miş
    0.58
    ..............
    0.57
    ~~~~~~~~
    0.55
     där
    0.55
    ~~~~
    0.55
    ası
    0.54
    startTime
    0.54
     البته
    0.54
    ’.
    0.54
    POSITIVE LOGITS
    errMsg
    0.80
     frightened
    0.74
     ridiculus
    0.72
    <unused951>
    0.70
     Alloys
    0.70
     Fear
    0.70
     moch
    0.70
    Subsec
    0.69
     президент
    0.68
    Ls
    0.67
    Activations Density 0.001%

    No Known Activations