© 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. 40-GEMMASCOPE-2-RES-262K
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    act, buy, motivations, drum, looked

    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_40_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
    вили
    0.45
     lakukan
    0.42
    <0x0F>
    0.42
    ikations
    0.41
    Caso
    0.41
    ூழ
    0.38
     fiber
    0.38
    ვით
    0.38
     preferencia
    0.38
     portions
    0.38
    POSITIVE LOGITS
    א
    0.58
     وير
    0.54
    education
    0.51
    ۳
    0.50
    ORM
    0.50
     chỉ
    0.48
    ير
    0.48
    𝙶
    0.48
    Education
    0.47
     យើង
    0.47
    Activations Density 0.000%

    No Known Activations