© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8983
    Prev
    Next
    INDEX
    Explanations

    options or questions

    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_16k_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
    וק
    0.42
    С
    0.42
    ская
    0.38
    3
    0.38
     לס
    0.38
    ре
    0.36
    ор
    0.36
    ים
    0.35
    рас
    0.35
    Registration
    0.35
    POSITIVE LOGITS
     Đấy
    0.48
     jiné
    0.45
     Otras
    0.44
     proporcionar
    0.43
     Veränder
    0.42
     uguale
    0.42
     diğer
    0.41
     prefque
    0.41
     andere
    0.41
     logique
    0.41
    Activations Density 0.164%

    No Known Activations