© 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. 6985
    Prev
    Next
    INDEX
    Explanations

    creating and processing actions

    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
     stalking
    0.94
    less
    0.94
    ness
    0.85
    afety
    0.85
     witnessing
    0.83
    britann
    0.81
    ärk
    0.81
    <unused144>
    0.80
     organizing
    0.80
    lessness
    0.79
    POSITIVE LOGITS
     کردن
    1.22
    Existing
    1.08
     करके
    1.08
     Existing
    1.03
     ולה
    1.01
    并
    0.98
     করার
    0.97
    Single
    0.95
     সমস্ত
    0.95
    ovať
    0.94
    Activations Density 0.429%

    No Known Activations