© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7050
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    headings and bold text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سلاټ
    0.44
    𠄌
    0.41
     blurry
    0.40
     covariates
    0.39
     morphology
    0.38
     fuzzy
    0.38
     theorists
    0.38
     جوسینو
    0.37
     morphisms
    0.37
     ontology
    0.37
    POSITIVE LOGITS
    </strong>
    0.56
    :
    0.51
    ça
    0.43
    *:
    0.43
    </b>
    0.42
    </u>
    0.42
     EVENT
    0.42
    cliente
    0.41
    }:
    0.41
     feme
    0.41
    Activations Density 0.004%

    No Known Activations