© 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. 25800
    Prev
    Next
    INDEX
    Explanations

    conditional questions and statements

    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
     this
    -1.40
    썼
    -1.23
    ="">
    -1.20
    ֶּ
    -1.20
     biela
    -1.19
     trebui
    -1.18
     italie
    -1.18
    Vietnam
    -1.18
    untergang
    -1.18
    Philippines
    -1.16
    POSITIVE LOGITS
     limit
    1.13
    4
    1.09
     of
    1.08
     will
    1.06
    楽しむ
    1.05
    6
    1.05
    7
    1.04
    時も
    1.03
    Publié
    1.02
     is
    1.01
    Activations Density 0.005%

    No Known Activations