© 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. 16-GEMMASCOPE-2-RES-262K
    7. 105684
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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_16_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
    GALAD
    0.79
    ена
    0.73
    ند
    0.73
    ва
    0.72
    ﮐ
    0.69
    ra
    0.68
     esposo
    0.68
    alui
    0.68
    نی
    0.67
    ти
    0.66
    POSITIVE LOGITS
    At
    0.75
     was
    0.74
    a
    0.71
    Hel
    0.71
    Was
    0.70
    ه
    0.70
    As
    0.69
    ف
    0.68
    Cap
    0.64
    Man
    0.64
    Activations Density 0.001%

    No Known Activations