© 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. 62230
    Prev
    Next
    INDEX
    Explanations

    your property, Denmark websites

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

    before committing

    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
     membranes
    0.40
    差別
    0.40
     Katzen
    0.40
     microstructure
    0.39
    otherm
    0.39
    紋
    0.38
     criado
    0.37
    icture
    0.37
     Cobb
    0.36
    了他
    0.36
    POSITIVE LOGITS
    öglichkeiten
    0.50
    თვის
    0.47
     masing
    0.46
     लगातार
    0.45
     głównie
    0.44
    ชีพ
    0.44
    毕
    0.43
     प्रेग्नेंसी
    0.42
    നിര
    0.42
    даря
    0.42
    Activations Density 0.000%

    No Known Activations