© 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. 100189
    Prev
    Next
    INDEX
    Explanations

    title: Text

    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
    Mead
    0.41
    莜
    0.40
    unca
    0.40
    cC
    0.40
     trousers
    0.39
    Meg
    0.39
     மேம்ப
    0.39
     Meadow
    0.38
    icycl
    0.38
    üller
    0.38
    POSITIVE LOGITS
    霓
    0.41
     мл
    0.37
    ->
    0.37
     инде
    0.36
     公司
    0.35
    сторон
    0.35
     optimism
    0.35
     понимать
    0.35
    getCamera
    0.34
    甄
    0.34
    Activations Density 0.002%

    No Known Activations