© 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. 172570
    Prev
    Next
    INDEX
    Explanations

    leading industry technology

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

    always consult

    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
     rapporto
    0.59
    ای
    0.57
    ല
    0.53
     elucidate
    0.49
     resistenza
    0.49
    numero
    0.48
     comunica
    0.46
    WITH
    0.46
     bont
    0.45
     resonate
    0.44
    POSITIVE LOGITS
    ators
    0.51
     Agriculture
    0.47
     бясплат
    0.46
     प्राणियों
    0.46
    ians
    0.45
    amers
    0.43
    ského
    0.43
    蝓
    0.43
     উঠ
    0.42
     ግራም
    0.42
    Activations Density 0.000%

    No Known Activations