© 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. 10-GEMMASCOPE-RES-131K
    7. 7434
    Prev
    Next
    INDEX
    Explanations

    keyboard keys

    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_10/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
     Italie
    -1.59
     usi
    -1.48
    躓
    -1.44
    Iam
    -1.33
     ragaz
    -1.32
    :--
    -1.30
    毟
    -1.30
     they
    -1.28
    😭😭
    -1.28
     "--
    -1.27
    POSITIVE LOGITS
     Some
    1.51
     Makes
    1.41
     three
    1.38
     Additionally
    1.36
     increased
    1.35
     or
    1.34
     six
    1.32
    iramente
    1.32
     two
    1.30
     decreased
    1.30
    Activations Density 0.017%

    No Known Activations