© 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. 101925
    Prev
    Next
    INDEX
    Explanations

    quantities and specific figures

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

    describes typical characteristics

    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
    ست
    0.52
    نش
    0.46
    ور
    0.46
    p
    0.45
    KNOWN
    0.45
    رض
    0.45
    としても
    0.45
    نوان
    0.44
     USED
    0.43
    隅
    0.43
    POSITIVE LOGITS
     Отече
    0.50
     masquer
    0.49
    त्रेयी
    0.48
     compartments
    0.45
     தெரிவி
    0.45
    💘
    0.44
     discriminate
    0.44
     hæ
    0.43
     sweating
    0.43
     hatching
    0.43
    Activations Density 0.000%

    No Known Activations