© 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. 34-GEMMASCOPE-RES-131K
    7. 78831
    Prev
    Next
    INDEX
    Explanations

    confirm, prospect, retrospect

    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_34/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
    remot
    -1.05
     encontramos
    -1.02
     duża
    -0.99
     ให้
    -0.95
     の
    -0.94
     prosty
    -0.94
    btw
    -0.94
     wary
    -0.90
    attet
    -0.89
     protegida
    -0.88
    POSITIVE LOGITS
     professeurs
    1.23
     alun
    1.15
    teen
    1.14
    ry
    1.13
    ant
    1.09
     cio
    1.07
     misa
    1.06
    ­
    1.05
     nii
    1.05
     travailleurs
    1.04
    Activations Density 0.202%

    No Known Activations