© 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. 66228
    Prev
    Next
    INDEX
    Explanations

    continuation after words

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

    Abstract characteristics

    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
    чна
    0.52
     Borders
    0.52
    ష్య
    0.50
    東京
    0.47
     Acerca
    0.47
    ᠴ
    0.47
     hosped
    0.47
     Caribe
    0.47
    কর
    0.46
     NVARCHAR
    0.46
    POSITIVE LOGITS
    -
    0.48
    re
    0.45
    源
    0.45
    al
    0.44
     will
    0.43
    ATS
    0.42
    Presenter
    0.42
     reeling
    0.41
    Writer
    0.40
    ওয়ায়
    0.40
    Activations Density 0.001%

    No Known Activations