© 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. 21778
    Prev
    Next
    INDEX
    Explanations

    dash followed by citation indicator

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

    explains service, logic, or negative conditions

    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
    林
    0.42
     facades
    0.42
    ンドウ
    0.42
     maqu
    0.41
    sg
    0.41
    市政
    0.41
    ｎ
    0.41
    Rendering
    0.40
    Fox
    0.40
     수도
    0.40
    POSITIVE LOGITS
     gdyż
    0.50
     Theorie
    0.50
    થા
    0.44
    initial
    0.43
     初期
    0.41
    getMethod
    0.41
    堕
    0.40
     klinik
    0.40
    genommen
    0.40
    élim
    0.39
    Activations Density 0.000%

    No Known Activations