© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2746
    Prev
    Next
    INDEX
    Explanations

    how to

    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_16k_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
     رسول
    0.38
     दो
    0.37
    3
    0.37
    สม
    0.36
    4
    0.36
    革命
    0.36
     Федера
    0.35
    cstdlib
    0.34
    ３
    0.34
    Created
    0.34
    POSITIVE LOGITS
     nějak
    0.48
     ایسے
    0.46
     এরূপ
    0.45
     deleterious
    0.44
     QSOs
    0.43
     ilyen
    0.43
     pewno
    0.42
    তাস
    0.42
    🜨
    0.41
     solcher
    0.41
    Activations Density 0.907%

    No Known Activations