© 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. 128479
    Prev
    Next
    INDEX
    Explanations

    starts of proper nouns or lists

    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
     télécommande
    -1.32
     plainte
    -1.19
     conosce
    -1.17
     registrazione
    -1.15
     Erwä
    -1.14
     meille
    -1.13
     Luglio
    -1.12
     volontà
    -1.10
     always
    -1.09
     zafira
    -1.09
    POSITIVE LOGITS
     to
    1.68
    ंह
    1.17
    during
    1.13
     but
    1.11
     provi
    1.05
     consid
    1.03
     
    1.03
     "
    1.03
     evi
    1.02
    h
    1.01
    Activations Density 0.002%

    No Known Activations