© 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. 102677
    Prev
    Next
    INDEX
    Explanations

    explanation of details

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

    asks you to gain trust

    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
     funniest
    0.50
    atletas
    0.45
    FUNCION
    0.42
     trots
    0.42
     लिमिट
    0.41
    ```
    0.40
     vieille
    0.40
    कंपनी
    0.39
    peed
    0.39
     కొన్ని
    0.39
    POSITIVE LOGITS
    建筑
    0.43
     mortgage
    0.43
    ництво
    0.42
     mortgagee
    0.41
    u
    0.41
    ោម
    0.41
     স্থাপ
    0.41
     недвижи
    0.40
    致力于
    0.40
     particulières
    0.40
    Activations Density 0.001%

    No Known Activations