© 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. 28676
    Prev
    Next
    INDEX
    Explanations

    explaining software or processes

    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
     triangle
    0.44
    dominal
    0.44
     invited
    0.43
     satin
    0.43
    Triangle
    0.43
    horizontal
    0.43
     Maui
    0.43
    ?
    0.43
    acquisto
    0.42
     eyes
    0.42
    POSITIVE LOGITS
     workflows
    0.46
     марке
    0.46
    早
    0.45
    ์
    0.44
     Mathematik
    0.43
     업무
    0.43
     세상
    0.42
    рово
    0.42
    킷
    0.42
    鑄
    0.42
    Activations Density 0.002%

    No Known Activations