© 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-262K
    7. 6055
    Prev
    Next
    INDEX
    Explanations

    contrasting differences and comparisons

    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_262k_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
     +
    0.69
     optionally
    0.69
    starter
    0.69
     starter
    0.68
    <eos>
    0.68
    <start_of_image>
    0.67
     start
    0.67
     initial
    0.67
     (
    0.66
     Configure
    0.65
    POSITIVE LOGITS
     Ironically
    1.35
    Ultimately
    1.27
    Despite
    1.24
    However
    1.23
    Ironically
    1.23
    Interestingly
    1.22
     argues
    1.19
     Interestingly
    1.16
     Ultimately
    1.15
    It
    1.15
    Activations Density 0.123%

    No Known Activations