© 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. 27707
    Prev
    Next
    INDEX
    Explanations

    origins of things or people

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

    describing entities or concepts

    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
    Թ
    0.44
    عمال
    0.43
     shortcoming
    0.42
    Revised
    0.42
     симпто
    0.42
    atiti
    0.41
    Mis
    0.41
    腎
    0.41
     damned
    0.40
    EXAMPLES
    0.40
    POSITIVE LOGITS
     được
    0.49
     Joule
    0.48
    相同
    0.46
     Unity
    0.45
     Jockey
    0.44
     Fondation
    0.43
    जगी
    0.43
     Rotary
    0.42
     Rousseau
    0.41
     Kalah
    0.41
    Activations Density 0.000%

    No Known Activations