© 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. 170315
    Prev
    Next
    INDEX
    Explanations

    Author bio and Google services

    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
     вторая
    0.54
     кроме
    0.53
     первая
    0.53
     දක්
    0.52
    <unused1049>
    0.52
    с
    0.51
     elevationMap
    0.50
     مرتبہ
    0.49
     hérit
    0.49
     ሁለት
    0.49
    POSITIVE LOGITS
     your
    0.45
    Mode
    0.45
    g
    0.45
    诊
    0.43
     lifecycle
    0.42
     Glove
    0.42
    膦
    0.42
     fro
    0.42
    eco
    0.42
    maps
    0.42
    Activations Density 0.000%

    No Known Activations