© 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. 77300
    Prev
    Next
    INDEX
    Explanations

    praying . discovers waxing Braun

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

    technical tools and platforms

    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
     museo
    0.62
     Tint
    0.56
     molti
    0.55
    ূত
    0.55
    ᠯ
    0.55
     portare
    0.54
     conçu
    0.54
    ेटा
    0.54
     Corey
    0.54
     Spagna
    0.54
    POSITIVE LOGITS
    )$
    0.51
     (
    0.46
    MES
    0.46
    ни
    0.46
    }(
    0.45
    ,
    0.44
    BIUM
    0.43
    No
    0.41
    NAT
    0.41
     vortices
    0.41
    Activations Density 0.001%

    No Known Activations