© 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. 173447
    Prev
    Next
    INDEX
    Explanations

    access or beginning of phrases

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

    private legal marriage

    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
    廃
    0.49
    📻
    0.47
    arı
    0.46
     useless
    0.44
    ędz
    0.44
    経
    0.44
    換え
    0.43
    Philippines
    0.43
    ான்
    0.42
     नेक्स्ट
    0.42
    POSITIVE LOGITS
     accéder
    0.47
     cun
    0.46
    า
    0.45
     pozycji
    0.45
    فة
    0.45
    sheet
    0.43
     valle
    0.43
     khud
    0.43
     onyx
    0.43
    砼
    0.43
    Activations Density 0.000%

    No Known Activations