© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83878
    Prev
    Next
    INDEX
    Explanations

    explaining complex situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preprocess
    0.46
     Bohr
    0.46
     ல
    0.45
     equival
    0.44
     essentiellement
    0.44
     overlays
    0.43
     مقدم
    0.43
     prerequisites
    0.43
     sank
    0.42
     entradas
    0.42
    POSITIVE LOGITS
    glow
    0.54
    abhave
    0.54
    um
    0.52
    p
    0.52
    avacak
    0.52
    gete
    0.51
    ai
    0.51
    british
    0.50
    ной
    0.49
    netic
    0.49
    Activations Density 0.005%

    No Known Activations