© 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. 119265
    Prev
    Next
    INDEX
    Explanations

    come + direction or state

    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
    审美
    0.40
     vases
    0.40
     lifted
    0.39
     ahorrar
    0.39
     prona
    0.39
    ڕ
    0.39
    ペア
    0.38
    <unused359>
    0.38
    钅
    0.38
     unsol
    0.38
    POSITIVE LOGITS
     \{\
    0.46
    Override
    0.41
    ard
    0.40
     Algorithm
    0.39
     Wen
    0.39
     Strait
    0.39
     hypothesis
    0.38
    hypothesis
    0.38
     Pat
    0.38
     Targ
    0.38
    Activations Density 0.005%

    No Known Activations