© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76861
    Prev
    Next
    INDEX
    Explanations

    expressing thoughts and complexities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     받
    0.41
     ११
    0.38
     triggering
    0.37
     ગયા
    0.37
    ıları
    0.37
    ㊙
    0.37
     বিশ্বাস
    0.37
     pretended
    0.36
     उत्तराखंड
    0.36
    諸
    0.36
    POSITIVE LOGITS
    :
    0.44
    और
    0.38
    baik
    0.38
    riad
    0.36
    gerald
    0.36
    ikas
    0.35
    :\
    0.35
    amburger
    0.35
    mehr
    0.34
    /@
    0.34
    Activations Density 0.249%

    No Known Activations