© 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. 196442
    Prev
    Next
    INDEX
    Explanations

    would be great

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

    planning blocks of time

    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
     ની
    0.51
     сві
    0.48
    ｹ
    0.48
     carri
    0.45
     giapp
    0.45
    ケ
    0.44
     questione
    0.43
    粧
    0.43
    al
    0.43
    स
    0.43
    POSITIVE LOGITS
    </strong>
    0.50
    حدث
    0.46
    Примечания
    0.44
    </h1>
    0.42
    struct
    0.42
    ArrayList
    0.40
    Histogram
    0.40
     نر
    0.39
    ierungen
    0.39
    ليم
    0.39
    Activations Density 0.002%

    No Known Activations