© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46104
    Prev
    Next
    INDEX
    Explanations

    because it's about explanations

    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
     also
    0.50
    also
    0.47
    烂
    0.40
     implicitly
    0.40
    Also
    0.39
    Expr
    0.39
    BOSTON
    0.38
    爲
    0.38
    tasks
    0.38
    ane
    0.38
    POSITIVE LOGITS
     karena
    0.51
     pédicule
    0.49
    ewnątrz
    0.47
    是因為
    0.47
     aufgrund
    0.47
     menyebabkan
    0.46
     omdat
    0.46
     wanneer
    0.45
     haven
    0.45
     debido
    0.45
    Activations Density 0.019%

    No Known Activations