© 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. 163049
    Prev
    Next
    INDEX
    Explanations

    characters, touch, fibrosis, records

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

    ChatGPT capabilities and features

    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
    čina
    0.44
     struggled
    0.42
    ្ត
    0.42
    integrity
    0.42
     (<
    0.41
    jectories
    0.40
    erné
    0.40
     StatelessWidget
    0.39
     ashamed
    0.39
     misled
    0.39
    POSITIVE LOGITS
    ほか
    0.47
    怎样
    0.44
     timetable
    0.43
    怎樣
    0.43
     yapan
    0.43
    ടതി
    0.42
     paintbrush
    0.42
    India
    0.41
    Ꭽ
    0.41
     rien
    0.41
    Activations Density 0.002%

    No Known Activations