© 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. 222248
    Prev
    Next
    INDEX
    Explanations

    complimentary make-up white glove reading lump sum

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

    university or technology keywords

    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
    漆
    0.53
    같이
    0.52
    田
    0.51
    甘
    0.50
    ﻌ
    0.49
    武器
    0.47
    逸
    0.47
    ід
    0.46
    炸
    0.46
    地
    0.45
    POSITIVE LOGITS
     aps
    0.52
     dag
    0.51
     lī
    0.50
     कोस
    0.50
     öst
    0.50
     რამდ
    0.50
     amt
    0.50
     reparar
    0.50
     finden
    0.49
     Evalu
    0.49
    Activations Density 0.000%

    No Known Activations