© 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. 5326
    Prev
    Next
    INDEX
    Explanations

    bullet points, lists, examples

    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
    র্ষি
    0.37
    RatingDiff
    0.35
     childnya
    0.31
     sparsim
    0.31
     computeEncoder
    0.29
     meriye
    0.29
    widetilde
    0.29
    𝟏
    0.29
    ܨ
    0.28
     pptn
    0.28
    POSITIVE LOGITS
     characteristics
    0.33
     the
    0.32
     idealized
    0.32
    或
    0.31
    0.30
     Processes
    0.30
    描述
    0.30
     use
    0.29
     که
    0.29
    the
    0.29
    Activations Density 0.169%

    No Known Activations