© 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. 199640
    Prev
    Next
    INDEX
    Explanations

    physical therapy schools

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

    how to solve

    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
    urls
    0.47
    url
    0.46
    اح
    0.45
     avevo
    0.45
    נ
    0.43
     גבוה
    0.43
    Come
    0.42
    ಯ್ಯ
    0.42
    তিক
    0.42
     avevano
    0.41
    POSITIVE LOGITS
    㐸
    0.47
     dichotom
    0.46
    ៧
    0.46
     காட்ச
    0.46
     සහ
    0.45
    畂
    0.45
     concisely
    0.45
     succinctly
    0.44
     உடன
    0.44
     பிரச்சினை
    0.44
    Activations Density 0.001%

    No Known Activations