© 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. 164729
    Prev
    Next
    INDEX
    Explanations

    efficient, potential, place, operation, province

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

    very specific or literal constructions

    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
     leaked
    0.49
     lipstick
    0.48
     teori
    0.48
     penc
    0.48
     namanya
    0.47
    r
    0.47
     Soho
    0.46
    می
    0.45
    Vendor
    0.45
     lintas
    0.45
    POSITIVE LOGITS
     BOARDSIZE
    0.45
     योग्य
    0.43
    悔
    0.43
     为了
    0.42
    竞争力
    0.41
    髗
    0.40
    iler
    0.40
    週
    0.40
     Analysts
    0.40
    ს
    0.40
    Activations Density 0.000%

    No Known Activations