© 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. 242564
    Prev
    Next
    INDEX
    Explanations

    loan therefore, Mediates

    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
     kurzen
    0.43
    Toy
    0.43
    鹄
    0.43
    urp
    0.42
    icuous
    0.42
     પ્રમા
    0.42
     преобразова
    0.42
     употреб
    0.41
    が多く
    0.41
     आसानी
    0.41
    POSITIVE LOGITS
     erythe
    0.49
    dport
    0.46
    जहां
    0.46
    ول
    0.44
     axonal
    0.44
    ভের
    0.44
    旿
    0.44
     dependents
    0.44
    पिछले
    0.43
     glazing
    0.43
    Activations Density 0.000%

    No Known Activations