© 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. 20673
    Prev
    Next
    INDEX
    Explanations

    with or without

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

    warnings about cautions

    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
     працю
    0.59
    轨道
    0.54
     найкра
    0.54
    钢
    0.54
     инфра
    0.53
     клет
    0.53
     швидко
    0.53
    芘
    0.53
     кора
    0.53
     энергия
    0.53
    POSITIVE LOGITS
     regimens
    0.45
     detoxification
    0.44
     legitim
    0.44
     hiding
    0.43
    Monday
    0.42
     boxers
    0.42
     increase
    0.41
     alignment
    0.41
    em
    0.40
     scaling
    0.40
    Activations Density 0.000%

    No Known Activations