© 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. 182574
    Prev
    Next
    INDEX
    Explanations

    description, caption, features, adjustable

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

    common phrases and sequences

    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
    datal
    0.50
     inscribed
    0.46
    proc
    0.46
    dataPath
    0.45
    |_{\
    0.44
     эпо
    0.44
    mobility
    0.44
    fielder
    0.44
     یہودیوں
    0.43
    |");
    0.43
    POSITIVE LOGITS
    <0xBB>
    0.49
    ოლოგი
    0.45
     نروح
    0.45
     ক্লিন
    0.44
     mekan
    0.43
     hayvan
    0.42
    চক
    0.42
     DIEGO
    0.42
     soothe
    0.41
     görüntü
    0.41
    Activations Density 0.000%

    No Known Activations