© 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. 238139
    Prev
    Next
    INDEX
    Explanations

    neighborhood videos, receive cash, water analysis

    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
    **)
    0.46
    ’
    0.44
    кта
    0.43
    ****
    0.42
    ****/
    0.42
    阻
    0.42
    वत
    0.41
    易
    0.41
    кса
    0.41
     Arbitration
    0.41
    POSITIVE LOGITS
     عام
    0.49
     ऊपर
    0.48
     aligned
    0.47
     ഏക
    0.47
    香り
    0.47
     മനുഷ്യ
    0.46
     தலை
    0.45
     Nhiều
    0.44
    ặt
    0.44
     hypothes
    0.44
    Activations Density 0.001%

    No Known Activations