© 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-16K
    7. 726
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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_16k_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
    Ratio
    0.78
    Cooldown
    0.77
    પા
    0.77
    ሽ
    0.76
    Breath
    0.76
    Voltage
    0.75
    Tunnel
    0.74
    દો
    0.73
    Rotation
    0.73
    Pressure
    0.72
    POSITIVE LOGITS
     ailing
    1.00
    ᐈ
    0.99
    こうした
    0.98
     erfolgreich
    0.98
     cybersecurity
    0.96
     nonprofit
    0.95
    学ぶ
    0.94
     struggling
    0.94
     disseminating
    0.94
    するための
    0.93
    Activations Density 0.599%

    No Known Activations