© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117725
    Prev
    Next
    INDEX
    Explanations

    former roles

    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
    currently
    -1.13
     шанс
    -1.08
    たとえば
    -1.05
    目前
    -1.03
     replays
    -1.02
     mangled
    -1.02
    というわけで
    -0.99
     pares
    -0.96
    фильм
    -0.93
     peintre
    -0.93
    POSITIVE LOGITS
     military
    1.45
     employee
    1.38
     army
    1.29
     president
    1.23
     naval
    1.22
     child
    1.21
     member
    1.13
     employees
    1.13
     high
    1.12
     police
    1.12
    Activations Density 0.063%

    No Known Activations