© 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. 225939
    Prev
    Next
    INDEX
    Explanations

    Frida Kahlo

    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
    usr
    0.46
    upa
    0.45
    åg
    0.45
    考古
    0.43
    iting
    0.42
    ört
    0.42
    ů
    0.42
    ᴛ
    0.41
    aja
    0.41
    afar
    0.41
    POSITIVE LOGITS
     switched
    0.48
     ವೆ
    0.48
     especiais
    0.47
    Cases
    0.47
     subdirectory
    0.46
    媢
    0.46
     presently
    0.45
     aspectos
    0.44
     electrified
    0.44
     immersed
    0.43
    Activations Density 0.004%

    No Known Activations