© 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. 247210
    Prev
    Next
    INDEX
    Explanations

    fifty

    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
     města
    0.52
    鿢
    0.51
    ంటి
    0.46
    ры
    0.45
    лки
    0.45
     miasta
    0.45
    йдз
    0.45
    प्ताह
    0.45
     społecz
    0.44
     Beziehung
    0.44
    POSITIVE LOGITS
     पचास
    0.48
    颏
    0.47
    isub
    0.46
    edil
    0.46
    unud
    0.46
    Fifty
    0.44
     کرده
    0.43
     اشک
    0.43
     discarded
    0.43
    fifty
    0.43
    Activations Density 0.001%

    No Known Activations