© 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. 212672
    Prev
    Next
    INDEX
    Explanations

    NE Buckys

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

    language response types

    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
    نن
    0.52
     QuantityOnHand
    0.49
     استعمال
    0.48
    fiction
    0.47
    onics
    0.47
     усіх
    0.46
    呕
    0.46
    ዻ
    0.46
    Guitar
    0.46
    }_{[
    0.46
    POSITIVE LOGITS
     laborious
    0.52
     bernama
    0.50
     Cameroon
    0.48
     kandungan
    0.47
     amass
    0.47
     maximize
    0.47
     sponsored
    0.46
     gestire
    0.46
     indist
    0.46
     Implications
    0.46
    Activations Density 0.000%

    No Known Activations