© 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. 244048
    Prev
    Next
    INDEX
    Explanations

    locations and identifiers

    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
     dakkh
    0.54
    फी
    0.52
    ду
    0.50
     тести
    0.49
     МО
    0.48
    ժ
    0.48
     двор
    0.47
    ита
    0.46
    irikan
    0.46
     эн
    0.46
    POSITIVE LOGITS
    a
    0.70
            
    0.57
    Plant
    0.55
    Note
    0.53
    Teacher
    0.52
    Light
    0.52
    plant
    0.50
    Face
    0.50
    Wear
    0.49
    Hand
    0.49
    Activations Density 0.001%

    No Known Activations