© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43324
    Prev
    Next
    INDEX
    Explanations

    acts, force, processed, armature

    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
     вдруг
    -1.38
    esos
    -1.27
     in
    -1.24
    oshiba
    -1.18
    Phal
    -1.14
    Morfo
    -1.10
    monių
    -1.10
     esimer
    -1.09
    íslu
    -1.06
    routers
    -1.06
    POSITIVE LOGITS
    rogels
    1.37
     
    1.27
     además
    1.26
    ;
    1.23
    ORS
    1.22
    ؛
    1.21
    outs
    1.21
    INS
    1.20
    INES
    1.20
    where
    1.16
    Activations Density 0.107%

    No Known Activations