© 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. 98158
    Prev
    Next
    INDEX
    Explanations

    explicitly, not, but

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

    search verify use 5

    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
    陘
    0.53
    ѡ
    0.50
     reducer
    0.48
    ዴት
    0.47
    መም
    0.46
     Besoin
    0.44
     largeur
    0.44
     domaine
    0.43
    ঘ্র
    0.43
    TypeId
    0.43
    POSITIVE LOGITS
     explicitly
    0.46
    ဤ
    0.46
     Incorpor
    0.45
     Podcasts
    0.44
     Explicit
    0.42
    il
    0.42
     obscure
    0.42
    explicit
    0.41
     Petitioner
    0.41
    )。
    0.41
    Activations Density 0.000%

    No Known Activations