© 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. 38917
    Prev
    Next
    INDEX
    Explanations

    square root of

    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
    daki
    0.58
     quatro
    0.57
    ق
    0.54
    ික
    0.52
     groot
    0.52
    زان
    0.51
    زا
    0.50
     چهار
    0.50
    ڈا
    0.50
    س
    0.50
    POSITIVE LOGITS
    able
    0.62
    ening
    0.49
    ive
    0.45
    olytic
    0.44
    ation
    0.44
     depository
    0.43
     of
    0.42
     involvement
    0.42
     phosphorus
    0.42
     receptive
    0.42
    Activations Density 0.010%

    No Known Activations