© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4196
    Prev
    Next
    INDEX
    Explanations

    open [noun/adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     inay
    0.82
     ausz
    0.74
     ots
    0.72
    കളുടെ
    0.72
     జ్ఞాప
    0.71
    ುದು
    0.71
    }}(-
    0.70
     mania
    0.70
    કે
    0.69
     ktorí
    0.68
    POSITIVE LOGITS
     doors
    1.30
    ended
    1.18
    weathermap
    1.11
     ended
    1.08
     дверей
    1.06
    doors
    1.05
    streetmap
    1.02
    Ended
    1.01
    ="("
    1.00
     portas
    1.00
    Activations Density 0.110%

    No Known Activations