© 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. 125489
    Prev
    Next
    INDEX
    Explanations

    official documents and policy

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

    various languages

    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
    ى
    0.50
    说到
    0.47
    رو
    0.46
    ၢ
    0.44
    ustan
    0.42
     pede
    0.41
     denomin
    0.41
    otta
    0.40
    ل
    0.40
    ាក
    0.39
    POSITIVE LOGITS
     ανθρώ
    0.55
     semaines
    0.55
     weekdays
    0.50
    quée
    0.50
     CAE
    0.49
     вій
    0.49
     appliquée
    0.49
     Saturdays
    0.47
     tôt
    0.47
     Vaughn
    0.47
    Activations Density 0.000%

    No Known Activations