© 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. 175976
    Prev
    Next
    INDEX
    Explanations

    do what

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

    technical 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
    Ž
    0.50
    ERR
    0.48
    Output
    0.45
    ič
    0.44
    ede
    0.44
    nae
    0.44
    IP
    0.43
    Declaration
    0.42
    <
    0.41
    ade
    0.41
    POSITIVE LOGITS
    த்திலும்
    0.54
    ຈັດສົ່ງ
    0.50
     ιστο
    0.48
    ຈາກ
    0.47
     πριν
    0.46
    ຄວ
    0.46
    बहु
    0.45
     gorges
    0.45
     desenvolvimento
    0.45
    ഗീയ
    0.44
    Activations Density 0.001%

    No Known Activations