© 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. 129223
    Prev
    Next
    INDEX
    Explanations

    training how to install

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

    server guarding

    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
    㪇
    0.51
     wodurch
    0.50
    sluš
    0.50
     கூற
    0.49
    NgramModel
    0.46
    acter
    0.45
    acterial
    0.45
    št
    0.45
    što
    0.45
    㡀
    0.45
    POSITIVE LOGITS
    ہ
    0.57
     CBA
    0.55
     CLA
    0.53
     premium
    0.50
     TBA
    0.50
     Premium
    0.49
     Federal
    0.48
     CLT
    0.48
     computing
    0.48
     Oral
    0.47
    Activations Density 0.001%

    No Known Activations