© 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. 188602
    Prev
    Next
    INDEX
    Explanations

    related to

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

    un happy, seeking melodies, securing loans, represents free

    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
    ı
    0.49
    位相
    0.43
    BibitemShut
    0.41
    υκ
    0.41
     njima
    0.41
    》。
    0.40
    )。
    0.39
    ِی
    0.39
    色の
    0.39
    ).
    0.39
    POSITIVE LOGITS
    اؤ
    0.46
     داده
    0.44
     माल
    0.43
    าว
    0.43
     vitesse
    0.43
     progres
    0.43
    Uit
    0.42
    โล
    0.42
     rythme
    0.42
    Après
    0.42
    Activations Density 0.002%

    No Known Activations