© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78833
    Prev
    Next
    INDEX
    Explanations

    cold

    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
    u
    0.50
    erat
    0.49
     Monitor
    0.48
    ﺓ
    0.47
    ות
    0.46
    aq
    0.45
    WhiteRatingDiff
    0.45
    ations
    0.44
    ener
    0.44
    cribed
    0.44
    POSITIVE LOGITS
     cold
    1.52
     frío
    1.41
    Cold
    1.37
    cold
    1.37
    冷
    1.34
    冷的
    1.33
     холод
    1.30
     Cold
    1.22
     frio
    1.22
     fría
    1.18
    Activations Density 0.076%

    No Known Activations