© 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. 143417
    Prev
    Next
    INDEX
    Explanations

    needed to, digest foods, Application Layer

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

    price, antioxidant, or effect

    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
     ไ
    0.53
     đối
    0.50
    าว
    0.46
     ਸਾ
    0.44
     αι
    0.43
     OUTER
    0.43
     phir
    0.42
     bulge
    0.42
     Ireland
    0.41
     notre
    0.41
    POSITIVE LOGITS
    aprend
    0.52
     acompañada
    0.49
    éditeur
    0.46
     lembra
    0.46
     vendedores
    0.46
    ;\
    0.45
     учащихся
    0.44
    Alumno
    0.44
    attend
    0.44
    ọc
    0.43
    Activations Density 0.001%

    No Known Activations