© 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. 204579
    Prev
    Next
    INDEX
    Explanations

    suitability for, would step aside

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

    contrasting conjunctions and possessives

    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
     方法
    0.49
    ｉ
    0.48
     nutritious
    0.48
     可能
    0.48
    apanam
    0.48
    ingredient
    0.47
    ୃ
    0.47
     ガ
    0.46
     confectionery
    0.46
    exists
    0.45
    POSITIVE LOGITS
     Aline
    0.50
     Kein
    0.49
     الجرس
    0.45
     Rend
    0.44
     Kisi
    0.42
    Jeg
    0.42
     Tutor
    0.42
    ాలి
    0.41
     massif
    0.41
     takip
    0.41
    Activations Density 0.001%

    No Known Activations