© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15753
    Prev
    Next
    INDEX
    Explanations

    numerical assignments and codes

    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_40_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
     खाई
    0.43
     spat
    0.42
     kiek
    0.40
    ईद
    0.40
    প্রায়
    0.40
     नाज
    0.39
    裱
    0.39
    Toplam
    0.38
     իր
    0.38
    zące
    0.38
    POSITIVE LOGITS
     codes
    0.83
     Codes
    0.68
     code
    0.67
     коды
    0.66
     código
    0.65
    codes
    0.64
     १
    0.63
     códigos
    0.62
     ১
    0.61
    =-
    0.59
    Activations Density 0.024%

    No Known Activations