© 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. 159237
    Prev
    Next
    INDEX
    Explanations

    as, through, description, also, interested

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

    specific terms and concepts

    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
    击
    0.51
     victoire
    0.48
     checksum
    0.45
    ைகிறது
    0.45
     astr
    0.45
     Побе
    0.45
     tod
    0.45
     deaminase
    0.44
    ሐ
    0.44
     kraju
    0.43
    POSITIVE LOGITS
    üren
    0.52
    auern
    0.51
    agati
    0.50
    meshes
    0.50
    im
    0.50
    atanga
    0.48
    పాల
    0.47
    entions
    0.47
     പ്രേ
    0.47
    abek
    0.47
    Activations Density 0.001%

    No Known Activations