© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    feature extraction, request, engineering

    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
    л
    2.06
    ة
    1.99
    es
    1.80
    i
    1.59
    가
    1.54
    ת
    1.46
    תה
    1.38
    ات
    1.37
    ي
    1.30
    us
    1.29
    POSITIVE LOGITS
     prominently
    2.96
    tte
    2.37
    ttes
    1.94
    tted
    1.64
    erings
    1.58
    alty
    1.55
    ্সের
    1.54
    fulness
    1.50
    erd
    1.50
     dislocations
    1.49
    Activations Density 0.039%

    No Known Activations