© 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. 163397
    Prev
    Next
    INDEX
    Explanations

    licensing, reselling, or building into another product

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

    technical terms and their definitions

    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
     kê
    0.45
    땅
    0.43
     уви
    0.42
    且
    0.42
     Bumi
    0.42
    রাং
    0.41
    란
    0.41
     Perd
    0.40
     této
    0.40
    进去
    0.40
    POSITIVE LOGITS
    ಬಹುದ
    0.47
    aucune
    0.47
     failures
    0.46
    edor
    0.45
     recalculated
    0.45
    nostic
    0.44
     inhomogeneities
    0.44
    IGO
    0.44
     critica
    0.44
    Ç
    0.44
    Activations Density 0.001%

    No Known Activations