© 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. 239293
    Prev
    Next
    INDEX
    Explanations

    date and time indicators

    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
     joints
    0.47
    Tokenizer
    0.46
    Directories
    0.46
    Diameter
    0.46
    Manus
    0.46
     mast
    0.45
    }^{[
    0.45
     cords
    0.45
     tracts
    0.45
     manifestations
    0.45
    POSITIVE LOGITS
    铤
    0.48
    嘞
    0.47
     dėl
    0.47
     Thursday
    0.47
     त्यानंतर
    0.47
     Sunday
    0.45
     त्यांच्या
    0.45
    唯一
    0.44
    acept
    0.44
    唯一的
    0.44
    Activations Density 0.001%

    No Known Activations