© 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. 128681
    Prev
    Next
    INDEX
    Explanations

    give to someone

    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
     friv
    -1.55
    ὺς
    -1.48
     to
    -1.45
    你会
    -1.45
     untuk
    -1.45
     fredag
    -1.44
     torsdag
    -1.44
     instead
    -1.42
    你有
    -1.42
    ställning
    -1.40
    POSITIVE LOGITS
    肫
    1.80
     oiseaux
    1.64
     candidatos
    1.55
    omials
    1.54
     」
    1.49
    𝕋
    1.48
     canaux
    1.48
     også
    1.45
    borderSide
    1.45
     dodatk
    1.44
    Activations Density 0.033%

    No Known Activations