© 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. 169302
    Prev
    Next
    INDEX
    Explanations

    electronic signature

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

    implementation preparation

    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
     प्रकारे
    0.46
    aun
    0.45
     представитель
    0.42
    keycode
    0.42
    nden
    0.41
    8
    0.41
     captures
    0.41
    dbjc
    0.41
    =>$
    0.41
    ssen
    0.40
    POSITIVE LOGITS
     preparazione
    0.57
     entrenamiento
    0.54
     तैयारी
    0.53
     inzwischen
    0.53
     Readiness
    0.52
     Deadline
    0.51
     preparation
    0.51
     Preparation
    0.51
     તૈય
    0.50
     preparado
    0.50
    Activations Density 0.000%

    No Known Activations