© 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. 181068
    Prev
    Next
    INDEX
    Explanations

    colour proofing

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

    crossover strategy

    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
    𝔬
    0.57
    𝔪
    0.49
    '\
    0.48
    徘
    0.47
    文
    0.47
     entityManager
    0.46
    곶
    0.46
    룰
    0.45
     opcoes
    0.44
     dört
    0.44
    POSITIVE LOGITS
     Jakob
    0.45
     unbeatable
    0.45
     শতাব্দীর
    0.44
     harmless
    0.43
     perennial
    0.43
     Sheldon
    0.43
     കണ്ട
    0.42
    iono
    0.42
     швидко
    0.41
     Karl
    0.41
    Activations Density 0.001%

    No Known Activations