© 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. 51729
    Prev
    Next
    INDEX
    Explanations

    of Allah; empty landscape; turn away

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

    power dynamics and imbalance

    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
    ાળા
    0.44
    合併
    0.42
     molds
    0.42
    ಂ
    0.41
    中間
    0.41
    ουμε
    0.41
     canceling
    0.40
     thermally
    0.40
    DAY
    0.40
     conserved
    0.40
    POSITIVE LOGITS
    chelles
    0.48
     بسیاری
    0.47
     மாணவ
    0.47
     สืบค้น
    0.47
     واکنش
    0.44
    heri
    0.44
     겁
    0.44
    empi
    0.44
     reseñas
    0.43
     spectre
    0.43
    Activations Density 0.000%

    No Known Activations