© 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. 23146
    Prev
    Next
    INDEX
    Explanations

    comets

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

    ice and dust from space

    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
    लापूर
    0.49
    监狱
    0.48
    oksatta
    0.47
     получен
    0.43
    ᓐ
    0.42
    짭
    0.42
    =@@
    0.42
     мощность
    0.42
    ónico
    0.42
     convection
    0.41
    POSITIVE LOGITS
     comet
    0.59
     Comet
    0.55
     Hale
    0.48
     Wasch
    0.46
     Scare
    0.45
    彗
    0.45
     setImage
    0.44
     Sublime
    0.44
     Ceres
    0.44
     Bright
    0.43
    Activations Density 0.010%

    No Known Activations