© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    referred to, differences between, no sooner

    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
     بيها
    -0.88
    ύν
    -0.88
    northeast
    -0.85
    $}
    -0.84
    neder
    -0.82
    anwal
    -0.82
    Firebase
    -0.82
    enegal
    -0.81
    banez
    -0.80
    łby
    -0.79
    POSITIVE LOGITS
     instead
    0.76
    的身影
    0.73
     said
    0.71
    riculture
    0.69
    veillance
    0.69
    AAAAAAAAAAAAAAAA
    0.69
    enguaje
    0.69
     culti
    0.68
    esque
    0.68
     belliger
    0.68
    Activations Density 0.007%

    No Known Activations