© 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. 200321
    Prev
    Next
    INDEX
    Explanations

    names after "with" or "before"

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

    Vercel, Kubernetes, Bonds, Maintaining

    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
    ucar
    0.53
     أعمال
    0.51
    Ꮻ
    0.48
    Ꮑ
    0.47
    ikation
    0.46
    <unused32>
    0.44
     глав
    0.44
     челу
    0.43
    Ꮲ
    0.43
    ថ្ងៃ
    0.42
    POSITIVE LOGITS
     interven
    0.50
    Neon
    0.49
     Biennale
    0.48
     Neon
    0.47
     intervened
    0.46
     Ruch
    0.46
     Intervention
    0.45
     Silicone
    0.45
    دون
    0.44
     silicone
    0.43
    Activations Density 0.003%

    No Known Activations