© 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. 232760
    Prev
    Next
    INDEX
    Explanations

    Germany, Denmark, cookie

    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
     карта
    0.52
    ан
    0.50
     humming
    0.50
    ూ
    0.49
     intently
    0.46
     confirmed
    0.45
     тре
    0.45
    helium
    0.45
     салу
    0.45
     ballistic
    0.44
    POSITIVE LOGITS
     Afin
    0.50
    La
    0.49
    الو
    0.48
     Probleme
    0.47
    ertation
    0.46
    -])
    0.45
     Pozn
    0.45
    Melbourne
    0.44
     निशुल्क
    0.44
    Monter
    0.44
    Activations Density 0.000%

    No Known Activations