© 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. 17-GEMMASCOPE-2-RES-16K
    7. 122
    Prev
    Next
    INDEX
    Explanations

    zero or false

    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_17_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
    ,
    0.67
     in
    0.66
     per
    0.65
     for
    0.62
     am
    0.61
     more
    0.61
    …
    0.61
     or
    0.60
    ্যার
    0.58
     individual
    0.58
    POSITIVE LOGITS
    0
    1.57
    False
    1.19
    None
    1.17
     zeros
    1.06
    NaN
    1.05
    false
    1.03
    ٠
    1.02
    1
    1.01
    NULL
    1.00
     False
    0.99
    Activations Density 4.546%

    No Known Activations