© 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. 156175
    Prev
    Next
    INDEX
    Explanations

    inconsistent with password disabled

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

    information, pricing, accuracy

    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
    ver
    0.61
    ri
    0.47
    讨厌
    0.46
    von
    0.46
    ekt
    0.44
    эффици
    0.44
    Lock
    0.43
    "+"
    0.43
     percents
    0.43
    ۊ
    0.43
    POSITIVE LOGITS
     HOTEL
    0.51
     ſh
    0.48
     CAPACITY
    0.46
     шрифт
    0.45
     VOLUME
    0.45
    多家
    0.45
     PAID
    0.45
     drawed
    0.44
     MANUAL
    0.44
     geométricas
    0.44
    Activations Density 0.001%

    No Known Activations