© 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. 123432
    Prev
    Next
    INDEX
    Explanations

    screensavers, painting, or metal

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

    allows you to

    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
    ة
    0.47
     বঞ্চিত
    0.45
    喻
    0.45
     لطف
    0.44
     fanno
    0.44
     می‌شوند
    0.44
    عية
    0.42
     perpetuated
    0.42
     স্বীকৃতি
    0.42
     করেননি
    0.42
    POSITIVE LOGITS
    ৫
    0.48
    arrera
    0.47
    ২
    0.46
    METAL
    0.45
    பாய்
    0.44
    ueux
    0.44
     באי
    0.43
     foils
    0.43
     essayer
    0.43
     announcer
    0.43
    Activations Density 0.000%

    No Known Activations