© 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. 111246
    Prev
    Next
    INDEX
    Explanations

    modeling behavior or models

    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
     дизайнер
    0.48
     ஆர்
    0.44
    nbhd
    0.43
     યોજના
    0.42
     ಅವರ
    0.42
    brooke
    0.42
    瑉
    0.42
     வகையில்
    0.42
    目标的
    0.41
    目の
    0.40
    POSITIVE LOGITS
     &
    0.46
     and
    0.44
     containers
    0.43
     und
    0.43
     و
    0.42
     panic
    0.41
     Threat
    0.41
     कॉमे
    0.39
     и
    0.39
    licting
    0.39
    Activations Density 0.003%

    No Known Activations