© 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. 49821
    Prev
    Next
    INDEX
    Explanations

    equations and inequalities

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

    equations and inequalities

    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
    dagen
    0.47
     nejsou
    0.47
    молу
    0.46
    дентифика
    0.46
     není
    0.45
    هي
    0.44
     finden
    0.43
    俻
    0.43
     '');
    0.43
     };
    0.42
    POSITIVE LOGITS
    恋爱
    0.42
    ylate
    0.42
     Levit
    0.40
     Stopped
    0.40
    Wayne
    0.40
    Cock
    0.39
    stopped
    0.39
     favored
    0.38
    regulate
    0.38
    feeds
    0.38
    Activations Density 0.000%

    No Known Activations