© 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. 84569
    Prev
    Next
    INDEX
    Explanations

    multi-lingual texts

    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
    cosis
    0.51
    returnValue
    0.48
    \}.
    0.48
     Unfortunately
    0.47
     newsletter
    0.47
     aerodynamic
    0.47
    гих
    0.47
     obsessive
    0.46
    fang
    0.45
     karate
    0.45
    POSITIVE LOGITS
    alfi
    0.47
    د
    0.46
     einen
    0.44
    ალ
    0.43
    ICLE
    0.43
    Die
    0.43
    En
    0.42
     stejně
    0.42
    Na
    0.42
    Instit
    0.42
    Activations Density 0.003%

    No Known Activations