© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    4. followed by a specific item

    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
    อาด
    0.83
    ម្ល
    0.79
    Five
    0.78
    Seven
    0.74
     steig
    0.74
     Fifteen
    0.74
     climbed
    0.74
     ଗ
    0.73
    SetStr
    0.73
    Leading
    0.72
    POSITIVE LOGITS
    :
    1.10
    ,
    0.93
    ;
    0.92
    /
    0.85
     specific
    0.81
     miscellaneous
    0.81
    (
    0.80
    th
    0.79
     th
    0.76
     :
    0.74
    Activations Density 0.085%

    No Known Activations