© 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-65K
    7. 9422
    Prev
    Next
    INDEX
    Explanations

    implies expanding or consequences

    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_65k_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
    ால்
    0.48
     pastoral
    0.46
    녘
    0.46
    ვლი
    0.45
    ᱣ
    0.45
    ர்ஸ்
    0.44
    ွေ
    0.44
     aritmética
    0.44
     expeditions
    0.44
    াকার
    0.43
    POSITIVE LOGITS
    ("\
    0.52
     ville
    0.52
    ."
    0.51
    II
    0.51
    Consult
    0.51
     حاج
    0.48
    Phys
    0.47
    .</
    0.47
     ،
    0.47
     fort
    0.46
    Activations Density 0.005%

    No Known Activations