© 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. 124306
    Prev
    Next
    INDEX
    Explanations

    specific terms or packages

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

    negative consequences or disruption

    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
    3
    0.55
    Etudes
    0.51
    4
    0.50
    Rewards
    0.49
    Dan
    0.49
    wal
    0.48
    Dw
    0.48
    Lead
    0.47
    FAM
    0.47
    2
    0.47
    POSITIVE LOGITS
     ქ
    0.60
     thành
    0.51
    ស្ត
    0.51
     forested
    0.50
     alleviating
    0.49
     ста
    0.49
     physically
    0.49
     fiss
    0.48
     palp
    0.48
     disb
    0.48
    Activations Density 0.000%

    No Known Activations