© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66127
    Prev
    Next
    INDEX
    Explanations

    Object names and associated methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    剣
    -0.97
    ítani
    -0.91
    日语
    -0.87
     IAS
    -0.84
    culable
    -0.83
     Biographie
    -0.83
    rschein
    -0.82
    kebox
    -0.81
    Finished
    -0.80
     Martha
    -0.79
    POSITIVE LOGITS
     alip
    0.96
    娯
    0.82
    卻
    0.81
     bakso
    0.81
     like
    0.80
    ॆ
    0.80
    เติ
    0.79
     SOUTHERN
    0.79
     zdravot
    0.79
     bezw
    0.78
    Activations Density 0.008%

    No Known Activations