© 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. 200434
    Prev
    Next
    INDEX
    Explanations

    numbers, property, and medical conditions

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

    intentionality and direction

    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
     Alvarez
    0.47
     nigg
    0.47
     {
    0.46
     vann
    0.46
    0.46
     a
    0.44
     df
    0.44
     fl
    0.44
     labyrinth
    0.44
     gasp
    0.44
    POSITIVE LOGITS
     необхідно
    0.49
    State
    0.48
     prostředí
    0.47
    閾
    0.46
    ್ದ
    0.45
    SwingConstants
    0.45
    Connecticut
    0.45
    自動車
    0.44
     ም
    0.44
    Thoreau
    0.44
    Activations Density 0.001%

    No Known Activations