© 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. 197691
    Prev
    Next
    INDEX
    Explanations

    business promote percent

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

    statement editing Transportation like content Annotation “ a

    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
     со
    0.48
     Stoff
    0.46
     вещества
    0.46
    ):
    0.45
    ĕ
    0.44
     Paren
    0.44
     StringBuilder
    0.44
     многочис
    0.44
    ToRemove
    0.44
     Ex
    0.43
    POSITIVE LOGITS
    ವುದ
    0.49
     maxValue
    0.44
    Ꮒ
    0.43
    chanted
    0.42
     hoga
    0.42
    लियों
    0.41
     upright
    0.41
     citiz
    0.41
    ली
    0.40
     वहां
    0.40
    Activations Density 0.001%

    No Known Activations