© 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. 111248
    Prev
    Next
    INDEX
    Explanations

    condition to completion

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

    lists, titles, broadcasts, hope, listen, narrate

    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
    ഠ
    0.49
    ್ಟ
    0.46
    Hepinize
    0.45
    ЛА
    0.44
     клас
    0.44
     classi
    0.44
    クラス
    0.43
     остров
    0.43
    classes
    0.43
     투
    0.42
    POSITIVE LOGITS
    ৌত
    0.46
     ব্যতীত
    0.46
     ceases
    0.43
     cease
    0.41
     ceased
    0.40
    接收
    0.39
     adquisición
    0.38
     barter
    0.38
     ইস্য
    0.38
     disponibilidad
    0.38
    Activations Density 0.000%

    No Known Activations