© 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. 39503
    Prev
    Next
    INDEX
    Explanations

    locations and entities

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

    foreign and technical terms

    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
    ేక
    0.48
     Doming
    0.48
     Khalid
    0.47
     आरमारा
    0.47
     Leonard
    0.47
     hypersur
    0.46
    視
    0.46
    баты
    0.46
     Recruiting
    0.46
    쟈
    0.45
    POSITIVE LOGITS
     se
    0.47
    ukup
    0.45
    емость
    0.43
     normalised
    0.43
     realises
    0.43
    emporal
    0.42
     suffisamment
    0.42
    ได้รับการ
    0.42
    version
    0.41
     realised
    0.41
    Activations Density 0.000%

    No Known Activations