© 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. 235151
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
     ampliamente
    0.48
     தெரிவித்தார்
    0.46
     attiva
    0.46
     czasu
    0.45
    ாகி
    0.45
     uży
    0.45
    كان
    0.44
    લ
    0.44
     año
    0.44
    ر
    0.44
    POSITIVE LOGITS
     Boulder
    0.55
     Sachsen
    0.54
     Celtic
    0.51
     Bronze
    0.51
     Sask
    0.51
     Scorpion
    0.51
     Trident
    0.50
     WA
    0.50
     Berkeley
    0.49
     Labrador
    0.49
    Activations Density 0.000%

    No Known Activations