© 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. 26593
    Prev
    Next
    INDEX
    Explanations

    journal citations

    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
     what
    -1.20
    いただけます
    -1.13
     ostensibly
    -1.06
     rozwiązania
    -1.05
     journée
    -1.00
     arguably
    -1.00
    ！(
    -0.98
     (
    -0.97
     soluções
    -0.96
     úteis
    -0.96
    POSITIVE LOGITS
    Transk
    1.20
     mediante
    1.20
     incluso
    1.14
     ميد
    1.13
     recens
    1.12
     molte
    1.10
     появится
    1.09
    Salve
    1.04
     قوة
    1.04
    ę
    1.01
    Activations Density 0.022%

    No Known Activations