© 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. 169165
    Prev
    Next
    INDEX
    Explanations

    equally unpredictable or interesting, particular person

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

    initial atmosphere

    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
    ル
    0.61
    Beautiful
    0.50
    styling
    0.49
    DEFINITION
    0.48
    ITING
    0.47
    فيذ
    0.46
    Feeling
    0.46
    ت
    0.45
    Styl
    0.44
    EDITOR
    0.44
    POSITIVE LOGITS
     antes
    0.50
     babys
    0.47
     글로
    0.47
     दर
    0.45
    terra
    0.44
     apresenta
    0.43
     apresentam
    0.43
    axia
    0.43
     straightforward
    0.42
     acess
    0.42
    Activations Density 0.000%

    No Known Activations