© 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. 216924
    Prev
    Next
    INDEX
    Explanations

    « followed by a title

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

    not part of

    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
    確かに
    0.48
    真相
    0.46
    (^
    0.45
    嘏
    0.44
    瞟
    0.44
    Fot
    0.43
    lieb
    0.42
    zei
    0.42
    (
    0.42
    解答
    0.42
    POSITIVE LOGITS
     बढ़ा
    0.55
     belum
    0.52
     aumentado
    0.52
     antaranya
    0.51
     scuole
    0.49
     iniziale
    0.49
    ين
    0.48
    صار
    0.47
     antara
    0.47
     attuale
    0.47
    Activations Density 0.001%

    No Known Activations