© 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. 22-GEMMASCOPE-RES-131K
    7. 26967
    Prev
    Next
    INDEX
    Explanations

    coding comments and questions

    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
     männis
    -1.18
     ayudó
    -1.16
    geladen
    -1.13
    groet
    -1.09
     benefícios
    -1.07
     många
    -1.07
     kanyang
    -1.05
     rengi
    -1.03
    ᧐
    -1.02
    verlust
    -1.02
    POSITIVE LOGITS
     вашим
    1.20
    INTERVAL
    1.13
     seemed
    1.13
     had
    1.09
    了一会儿
    1.07
    ælde
    1.07
     remained
    1.05
     with
    1.05
    providedIn
    1.03
    étaient
    1.03
    Activations Density 0.008%

    No Known Activations