© 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. 205055
    Prev
    Next
    INDEX
    Explanations

    hot and cold conditions

    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
     warmth
    0.63
    温暖
    0.63
     tepl
    0.62
     warming
    0.61
     chaleur
    0.59
     тепло
    0.59
    暖
    0.58
    Heating
    0.57
     heating
    0.56
    heating
    0.56
    POSITIVE LOGITS
     (\<
    0.47
     Tutto
    0.46
     surfaces
    0.45
    Tout
    0.43
     (<
    0.43
    環境
    0.42
    tout
    0.42
     Tout
    0.42
     상태
    0.42
    ത്തിലൂടെ
    0.42
    Activations Density 0.009%

    No Known Activations