© 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. 181701
    Prev
    Next
    INDEX
    Explanations

    Alexandre Francesco

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

    defining or explaining

    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
    scattering
    0.45
    Ꭽ
    0.45
    ᕋ
    0.45
     φορ
    0.44
    ៀង
    0.44
     Ли
    0.43
     моде
    0.43
    ו
    0.43
    ಓ
    0.43
    mäßig
    0.42
    POSITIVE LOGITS
    THAN
    0.46
    HOSTNAME
    0.45
    INET
    0.43
     Alexandre
    0.42
    than
    0.41
     acreditar
    0.41
     Francesco
    0.41
     می‌باشد
    0.41
    حان
    0.41
     fidel
    0.40
    Activations Density 0.001%

    No Known Activations