© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17353
    Prev
    Next
    INDEX
    Explanations

    sudden sounds and shifts

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

    sudden change, then a description

    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_31_width_262k_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
    裔
    0.48
     помочь
    0.47
     경우에는
    0.47
     pondering
    0.46
    ównie
    0.42
     helpless
    0.41
     शत्र
    0.41
    akawa
    0.41
    徘
    0.40
     ischa
    0.39
    POSITIVE LOGITS
    鏘
    0.48
     instantaneously
    0.47
    !!!!!!
    0.45
    VEN
    0.42
     bam
    0.42
    💥
    0.42
     explodes
    0.41
    !!!!!!!
    0.41
    顿时
    0.40
     suddenly
    0.40
    Activations Density 0.021%

    No Known Activations