© 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. 174133
    Prev
    Next
    INDEX
    Explanations

    in Guinea or Germany

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

    format string

    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
     voiced
    0.46
     Azul
    0.42
    ’
    0.41
     সদস্য
    0.41
     اکثر
    0.41
     των
    0.40
     likewise
    0.40
     Cybersecurity
    0.40
     supporters
    0.39
    响
    0.39
    POSITIVE LOGITS
    alea
    0.45
    РО
    0.43
    rophy
    0.41
    rale
    0.41
    чности
    0.40
    iy
    0.40
     aslında
    0.40
    र्टी
    0.39
    ILLE
    0.38
    ilee
    0.38
    Activations Density 0.000%

    No Known Activations