© 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. 33643
    Prev
    Next
    INDEX
    Explanations

    that the

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

    hardware vs cloud services

    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
     nominally
    0.49
     કોઈ
    0.46
    و
    0.45
     setState
    0.45
    ل
    0.44
     最新
    0.44
     khoản
    0.43
     quill
    0.43
     Lately
    0.43
    ဝ
    0.43
    POSITIVE LOGITS
     meninggal
    0.43
     bebê
    0.43
     diferencias
    0.43
     Jepang
    0.43
    अमेर
    0.42
    ঘট
    0.41
    fonte
    0.40
     plonge
    0.40
     licensees
    0.40
    гава
    0.39
    Activations Density 0.000%

    No Known Activations