© 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. 4143
    Prev
    Next
    INDEX
    Explanations

    на + [verb/noun]

    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
     steeple
    0.70
     monsoon
    0.68
     मृतक
    0.68
     temperate
    0.67
     gespe
    0.67
    夎
    0.65
     انتقال
    0.65
    aupun
    0.64
     cu
    0.64
    pyrim
    0.63
    POSITIVE LOGITS
     практике
    0.69
     दाम
    0.57
    achet
    0.55
    ground
    0.54
     endonuclease
    0.54
    லு
    0.54
    terase
    0.53
     пись
    0.53
    實
    0.52
    min
    0.52
    Activations Density 0.126%

    No Known Activations