© 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. 193439
    Prev
    Next
    INDEX
    Explanations

    contract, branding, months, patients, marketers

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

    Pair new watch

    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
     якобы
    0.52
     إِل
    0.46
    𝐸
    0.45
     إِن
    0.43
    ០០
    0.43
     allegedly
    0.42
     يو
    0.42
     fluids
    0.41
    NESS
    0.41
     identically
    0.41
    POSITIVE LOGITS
    tire
    0.59
    hen
    0.54
     conosco
    0.53
    ті
    0.51
    тності
    0.51
     commandes
    0.50
     polisi
    0.50
    capac
    0.47
    сі
    0.47
    踴
    0.47
    Activations Density 0.000%

    No Known Activations