© 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. 111561
    Prev
    Next
    INDEX
    Explanations

    Iowa hospitals

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

    impact strength comparison

    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
    日記
    0.44
    指數
    0.43
     vorbe
    0.42
    詢
    0.42
    攔
    0.42
     öld
    0.42
     نريد
    0.42
     平
    0.41
     contient
    0.41
    能夠
    0.41
    POSITIVE LOGITS
    হাট
    0.51
     Clarion
    0.49
    শিক
    0.48
    ាហ
    0.47
    ذیر
    0.46
     mayoral
    0.46
     аутох
    0.44
    🍔
    0.43
     reimag
    0.43
    াপনের
    0.43
    Activations Density 0.001%

    No Known Activations