© 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. 100258
    Prev
    Next
    INDEX
    Explanations

    before UK

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

    mimicking and mirroring

    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
    বারের
    0.41
     invo
    0.41
    ե
    0.40
     aim
    0.40
    nya
    0.38
     reign
    0.38
    numerical
    0.38
    楨
    0.38
    мі
    0.38
    such
    0.37
    POSITIVE LOGITS
    🥖
    0.59
     пище
    0.54
     khử
    0.52
    uuuu
    0.52
    ).]
    0.51
    hhhh
    0.50
     короб
    0.50
    iccation
    0.50
    🎟
    0.49
    🥕
    0.49
    Activations Density 0.000%

    No Known Activations