© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45643
    Prev
    Next
    INDEX
    Explanations

    class extends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bv
    0.43
    леду
    0.41
     అందించ
    0.41
     以
    0.41
     أيام
    0.40
     outwe
    0.39
    流畅
    0.39
    ificate
    0.38
     enkele
    0.38
     szükséges
    0.38
    POSITIVE LOGITS
    পুন
    0.50
    row
    0.46
    дів
    0.44
    з
    0.44
    রা
    0.43
     pile
    0.43
    発電
    0.42
    ranno
    0.42
     reformulation
    0.42
    zea
    0.42
    Activations Density 0.000%

    No Known Activations