© 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. 75008
    Prev
    Next
    INDEX
    Explanations

    calculation bounces

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

    donations, replace, encryption, published

    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
     fase
    0.47
    imab
    0.46
    ροσ
    0.46
    罗斯
    0.44
    larger
    0.44
    ign
    0.44
    defined
    0.42
    仍
    0.42
    人为
    0.42
     vind
    0.42
    POSITIVE LOGITS
     ухуд
    0.52
     worsen
    0.48
     worsened
    0.46
     worsens
    0.45
     worsening
    0.45
     Tulum
    0.44
     Illness
    0.44
     있고
    0.43
    тье
    0.42
    ;
    0.42
    Activations Density 0.001%

    No Known Activations