© 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. 72230
    Prev
    Next
    INDEX
    Explanations

    object graph

    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
    ISSUE
    -0.79
     propia
    -0.78
     açúcar
    -0.76
     unfamiliar
    -0.73
     علاوه
    -0.71
     innovative
    -0.70
     erity
    -0.70
    तु
    -0.69
     Woodlands
    -0.69
    свое
    -0.69
    POSITIVE LOGITS
    ázaro
    0.97
     Talia
    0.81
     bantuan
    0.80
    我还是
    0.80
     seperti
    0.75
    ："
    0.75
     மற்றும்
    0.74
     (--
    0.73
    urige
    0.73
     njego
    0.72
    Activations Density 0.479%

    No Known Activations