© 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. 993
    Prev
    Next
    INDEX
    Explanations

    code assignments and data appending

    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
    <unused1112>
    0.44
     castor
    0.40
    <unused985>
    0.40
     silage
    0.38
    xcsche
    0.38
     zbyt
    0.38
    aktoren
    0.37
     ننوت
    0.36
     myosin
    0.36
    れの
    0.36
    POSITIVE LOGITS
     +=
    0.48
     I
    0.39
    ++;
    0.39
     |=
    0.39
    垪
    0.37
     If
    0.35
    +=
    0.35
     =
    0.35
    됩니다
    0.33
     This
    0.33
    Activations Density 0.066%

    No Known Activations