© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 46008
    Prev
    Next
    INDEX
    Explanations

    weapons and tools in use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
     coin
    0.49
     bomb
    0.46
     coins
    0.42
     bomba
    0.42
    毯
    0.41
    Coin
    0.40
     motores
    0.40
     richness
    0.39
     cubes
    0.39
     машинасы
    0.39
    POSITIVE LOGITS
     wield
    1.64
     wielding
    1.33
     swung
    0.92
     swinging
    0.85
     swings
    0.79
    挥
    0.79
     handle
    0.78
     swing
    0.75
     weapon
    0.74
     Swinging
    0.72
    Activations Density 0.031%

    No Known Activations