© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3683
    Prev
    Next
    INDEX
    Explanations

    snow, ice, and cold

    np_acts-logits-general · gemini-2.5-flash-lite

    ice and cold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姦
    0.43
    闿
    0.40
     রাজেশ
    0.38
    ार्टमेंट
    0.38
     Sept
    0.37
     ट्रायंगल
    0.37
     விநாயக
    0.36
     திரும
    0.36
     زائ
    0.36
    釁
    0.36
    POSITIVE LOGITS
     snow
    3.03
     freezing
    2.89
     बर्फ
    2.86
    凍
    2.86
     frozen
    2.83
    雪
    2.81
    冻
    2.81
     frost
    2.80
     icy
    2.77
    ❄
    2.77
    Activations Density 0.429%

    No Known Activations