© 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. 14736
    Prev
    Next
    INDEX
    Explanations

    list item markers

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

    privacy and links

    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
    ὼ
    0.49
    lx
    0.49
    ž
    0.48
    dyl
    0.48
    idé
    0.47
    erà
    0.46
     adaptée
    0.46
     семей
    0.46
     protectors
    0.45
    oare
    0.45
    POSITIVE LOGITS
     link
    0.47
     列
    0.45
     Nations
    0.44
     columnist
    0.43
     hypocrisy
    0.43
     intersection
    0.42
     लिंक
    0.41
     tweet
    0.41
     ट्वीट
    0.41
     Federalist
    0.41
    Activations Density 0.000%

    No Known Activations