© 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. 136435
    Prev
    Next
    INDEX
    Explanations

    migi-tate-seishan-dachi components

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

    behavioral advice

    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
     aumento
    0.45
     alturas
    0.44
     точки
    0.43
     incremento
    0.43
     aumenta
    0.43
     о
    0.42
     เอา
    0.42
     -----
    0.42
    Israel
    0.41
     là
    0.41
    POSITIVE LOGITS
     statesmen
    0.49
    rät
    0.47
    ٢
    0.45
    筮
    0.45
    მასრულ
    0.44
    白い
    0.43
     Hamiltonian
    0.43
     বহুম
    0.42
     renormalized
    0.42
     Nonlinear
    0.42
    Activations Density 0.000%

    No Known Activations