© 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. 114858
    Prev
    Next
    INDEX
    Explanations

    kilohertz

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

    phrasing and word order

    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
     nontrivial
    0.51
     Murphy
    0.49
     nonlinearity
    0.48
    ա
    0.46
     Versch
    0.46
     Yan
    0.45
     hind
    0.44
     স্কুলের
    0.43
    鲫
    0.43
    愔
    0.43
    POSITIVE LOGITS
    teurs
    0.48
    ết
    0.47
     gì
    0.47
     podendo
    0.45
     jogador
    0.44
     лигасы
    0.43
     capaz
    0.42
     pręd
    0.42
    距
    0.41
     desenvolvido
    0.41
    Activations Density 0.001%

    No Known Activations