© 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. 55481
    Prev
    Next
    INDEX
    Explanations

    discovered a, designed to, Robards

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

    granting powers/abilities

    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
     interf
    0.42
    했고
    0.41
     는
    0.40
    Fees
    0.40
     nœ
    0.40
     relates
    0.39
     गांवों
    0.39
    혐
    0.39
     gigs
    0.39
    🥅
    0.39
    POSITIVE LOGITS
     Zaragoza
    0.46
     знаний
    0.44
    髑
    0.44
     Hölder
    0.43
     Schwar
    0.43
    主人公
    0.42
    奇异
    0.41
     Salazar
    0.40
     Lloyds
    0.38
     Enzo
    0.38
    Activations Density 0.000%

    No Known Activations