© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    boundary objects or locations

    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
    the
    0.59
     the
    0.54
    ួន
    0.52
     Productions
    0.52
     Routing
    0.51
    The
    0.50
     값
    0.49
    äll
    0.49
     Economía
    0.49
    Ü
    0.48
    POSITIVE LOGITS
     vicinity
    0.86
     edges
    0.86
     periphery
    0.83
     outskirts
    0.83
     confines
    0.81
     sidelines
    0.80
     edge
    0.80
     forefront
    0.75
     midst
    0.74
     doorway
    0.72
    Activations Density 0.197%

    No Known Activations