© 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. 26033
    Prev
    Next
    INDEX
    Explanations

    array indices and mathematical operations

    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
    ***",
    0.47
     hayan
    0.45
     içerisinde
    0.45
    চ্ছিন্ন
    0.44
    ****",
    0.44
     dalamnya
    0.44
     jährlich
    0.43
    četně
    0.43
    াউন
    0.43
    녓
    0.42
    POSITIVE LOGITS
    b
    0.67
    c
    0.56
    k
    0.56
    d
    0.55
    s
    0.55
    p
    0.55
    f
    0.54
    and
    0.54
     and
    0.53
    r
    0.53
    Activations Density 0.050%

    No Known Activations