Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7437
    Prev
    Next
    INDEX
    Explanations

    regular expression patterns

    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_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
    (\
    0.79
     l
    0.79
     remains
    0.70
    (
    0.70
     are
    0.69
    (-
    0.68
     (
    0.67
    ('[
    0.65
     remain
    0.64
    en
    0.62
    POSITIVE LOGITS
    ÈRES
    1.01
     എത്തി
    0.91
    ನ್ನೆ
    0.91
    ÈRE
    0.90
     Recruitment
    0.88
    Gum
    0.88
     എത്ത
    0.88
     Química
    0.88
     Sheraton
    0.86
     commendable
    0.86
    Activations Density 0.002%

    No Known Activations