© 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. 1954
    Prev
    Next
    INDEX
    Explanations

    subsequent temporal sequencing

    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
     exist
    0.66
     reveal
    0.63
     Reveal
    0.61
     sliding
    0.61
     Tile
    0.61
     Stack
    0.60
    -
    0.60
    Χ
    0.59
     Slide
    0.59
     наход
    0.59
    POSITIVE LOGITS
     subsequently
    0.86
     then
    0.78
     سپس
    0.77
     thence
    0.76
    然后
    0.75
    katore
    0.74
     vervolgens
    0.73
    yani
    0.73
     conduits
    0.72
     conduit
    0.72
    Activations Density 0.000%

    No Known Activations