© 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-262K
    7. 52320
    Prev
    Next
    INDEX
    Explanations

    feeling and abstract concepts like facts

    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_262k_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
    San
    0.48
     Diwali
    0.47
    capi
    0.46
     Rabi
    0.46
    Compras
    0.46
    k
    0.46
    明星
    0.46
     has
    0.46
     máte
    0.46
     Blvd
    0.45
    POSITIVE LOGITS
     resignation
    0.48
     resign
    0.44
     derivations
    0.43
     onc
    0.41
     ።
    0.41
     abstract
    0.41
     daugiau
    0.40
    ید
    0.40
     humor
    0.40
     apl
    0.39
    Activations Density 0.002%

    No Known Activations