© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 31836
    Prev
    Next
    INDEX
    Explanations

    bottle caps

    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
     نمای
    0.39
    новниш
    0.37
    脑
    0.37
    })}$
    0.37
    ทยาลัย
    0.37
     Omnibus
    0.36
     Alessandra
    0.36
     सलाहकार
    0.36
    Dragging
    0.35
    溇
    0.35
    POSITIVE LOGITS
     bottle
    1.40
     bottles
    1.26
    bottle
    1.23
     Bottle
    1.21
    Bottle
    1.20
    瓶
    1.19
     ขวด
    1.09
     बोतल
    1.07
     cork
    1.06
     screw
    1.05
    Activations Density 0.021%

    No Known Activations