© 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. 226268
    Prev
    Next
    INDEX
    Explanations

    gel prior, thin coats

    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
     artich
    0.56
     应
    0.54
     冖
    0.54
     Сайт
    0.51
     volvió
    0.50
     Consulate
    0.50
     ángulo
    0.50
     четыре
    0.49
    Ἥ
    0.49
     arbre
    0.49
    POSITIVE LOGITS
    reise
    0.44
     ضرور
    0.43
     PEP
    0.41
    जर
    0.41
    N
    0.40
    Ob
    0.40
    ibuya
    0.40
    Vy
    0.39
    ラック
    0.38
    업
    0.38
    Activations Density 0.001%

    No Known Activations