© 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. 33572
    Prev
    Next
    INDEX
    Explanations

    positive outcome or requirement

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

    understanding why

    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
     ഉള്ള
    0.53
    දී
    0.51
     Суриков
    0.49
     பொருட்களை
    0.49
    ᱗
    0.48
     সৌমিত্র
    0.48
    ForSettings
    0.47
     použití
    0.47
     Función
    0.47
    TintMode
    0.47
    POSITIVE LOGITS
    ש
    0.48
    רי
    0.47
    י
    0.47
     MIDDLE
    0.44
    טר
    0.43
     stints
    0.42
     finances
    0.41
    necessarily
    0.40
    BLOCK
    0.39
     WILL
    0.39
    Activations Density 0.000%

    No Known Activations