© 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. 57196
    Prev
    Next
    INDEX
    Explanations

    groups control

    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
    ಾ
    0.46
     〢
    0.45
     POS
    0.44
     ব্যক্তিগত
    0.42
     Calibri
    0.42
     आल्सो
    0.41
     Malware
    0.41
    کاری
    0.41
     Caul
    0.41
     അവത
    0.41
    POSITIVE LOGITS
    шено
    0.49
     kurze
    0.45
     seism
    0.45
    زيز
    0.44
     heroin
    0.43
     exist
    0.42
    <0x85>
    0.42
     distribut
    0.41
     gente
    0.40
    리고
    0.40
    Activations Density 0.001%

    No Known Activations