© 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. 16581
    Prev
    Next
    INDEX
    Explanations

    to/across followed by a noun

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

    to step

    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
    opportunities
    0.46
    inspiring
    0.44
    ujah
    0.44
    ösungen
    0.44
    abileceğ
    0.43
    cdnjs
    0.43
     стрем
    0.42
    ▟
    0.42
     завое
    0.42
    arów
    0.41
    POSITIVE LOGITS
     casa
    0.45
    BE
    0.42
     ത
    0.42
     paid
    0.41
     bekend
    0.40
     permitem
    0.39
    くなる
    0.39
     maison
    0.39
    IEF
    0.39
    θη
    0.39
    Activations Density 0.000%

    No Known Activations