© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149662
    Prev
    Next
    INDEX
    Explanations

    stories without letters

    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_29_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
    ()}.
    0.97
     $($
    0.93
     semantics
    0.91
     semantic
    0.91
    ()}
    0.89
     ܠ
    0.88
     postural
    0.88
    ()}\
    0.87
     aber
    0.85
     volleyball
    0.84
    POSITIVE LOGITS
    ↵↵
    0.90
    Website
    0.75
    http
    0.68
    Ссылка
    0.65
    Inspection
    0.63
    link
    0.61
    jwa
    0.61
    వారి
    0.60
    ियन
    0.59
    Site
    0.59
    Activations Density 0.000%

    No Known Activations