© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4989
    Prev
    Next
    INDEX
    Explanations

    ice cream and cold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     Watford
    0.87
    佘
    0.82
     Cocker
    0.79
    뀌
    0.79
     Gyan
    0.79
     kebakaran
    0.79
     Yeast
    0.78
     Token
    0.78
     Fire
    0.78
     Fires
    0.76
    POSITIVE LOGITS
     ice
    1.69
     Ice
    1.60
    冰
    1.52
    Ice
    1.50
     freezer
    1.44
     Frozen
    1.37
     hielo
    1.27
    氷
    1.27
    アイス
    1.26
    Frozen
    1.25
    Activations Density 0.151%

    No Known Activations