© 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-262K
    7. 23173
    Prev
    Next
    INDEX
    Explanations

    connecting code and data

    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_262k_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
     délais
    0.42
     minimising
    0.39
     प्रेरणात्मक
    0.39
     dataType
    0.38
     requirements
    0.38
     player
    0.38
     deadlines
    0.38
    魯
    0.38
     unworthy
    0.37
    ⏺
    0.37
    POSITIVE LOGITS
    connect
    0.41
    Favorites
    0.40
    Bump
    0.39
    sous
    0.39
    Gener
    0.37
     connecté
    0.37
    \}$,
    0.36
    PNG
    0.36
    Connected
    0.36
    connected
    0.35
    Activations Density 0.029%

    No Known Activations