© 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. 60723
    Prev
    Next
    INDEX
    Explanations

    bed, mattress, product line

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

    focus on classification and speed

    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
    त्रेयी
    0.55
     स्टूडियो
    0.52
    antiation
    0.49
    🐨
    0.48
    ।
    0.47
    zam
    0.47
    🦦
    0.47
    :]:
    0.46
    ęła
    0.45
    anyl
    0.45
    POSITIVE LOGITS
     admitted
    0.45
     decom
    0.44
     electro
    0.43
    ಗರ
    0.42
     Spro
    0.42
    នឹង
    0.41
     declined
    0.41
     admissible
    0.41
    ឺ
    0.41
    లే
    0.40
    Activations Density 0.001%

    No Known Activations