© 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. 75202
    Prev
    Next
    INDEX
    Explanations

    person names and products

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

    eat up, sensation, meta insights, hit

    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
     створення
    0.46
    ForSettings
    0.46
    Arrival
    0.45
     британ
    0.44
    ISTAN
    0.44
     ແ
    0.44
    Lond
    0.43
     본격
    0.43
     제작
    0.42
    Sliced
    0.41
    POSITIVE LOGITS
     =
    0.46
     accountability
    0.45
     agrade
    0.44
    ))
    0.44
    か
    0.43
    現在
    0.43
     যাইহোক
    0.43
     হয়ত
    0.42
    かどうか
    0.42
     paycheck
    0.42
    Activations Density 0.004%

    No Known Activations