© 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. 129337
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

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

    explaining nuances or ranges

    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
    KeyValuePair
    0.50
    Datum
    0.50
    VERTISEMENT
    0.49
    Highlights
    0.46
    Excel
    0.46
    Estimation
    0.46
    JN
    0.46
    Ж
    0.46
    Citation
    0.45
    India
    0.45
    POSITIVE LOGITS
    atele
    0.57
     atuação
    0.49
    ira
    0.49
     spontaneous
    0.46
    antung
    0.46
    aniyati
    0.45
     দেয়ার
    0.45
    یرے
    0.44
     flavor
    0.44
     silky
    0.43
    Activations Density 0.000%

    No Known Activations