© 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. 166094
    Prev
    Next
    INDEX
    Explanations

    you might

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

    code descriptionsnumberspainting

    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
    Ἔ
    0.57
    Herk
    0.55
     задания
    0.53
     ткань
    0.52
    Ꮩ
    0.51
     hospitales
    0.50
    баев
    0.50
    Extend
    0.49
     majd
    0.49
     szko
    0.49
    POSITIVE LOGITS
     creepy
    0.50
     depreci
    0.50
     recl
    0.49
     These
    0.48
     a
    0.47
     me
    0.47
     cons
    0.47
     NOI
    0.46
     needed
    0.46
     Canonical
    0.46
    Activations Density 0.000%

    No Known Activations