© 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. 143287
    Prev
    Next
    INDEX
    Explanations

    average Irish, recognized;, home a, search for, buy Certified, then I, server is, extracted using

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

    avoiding different kinds

    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
     four
    0.51
     three
    0.45
     ၂
    0.44
    新型
    0.42
     backtracking
    0.41
     new
    0.41
    fi
    0.41
     incoming
    0.40
     back
    0.40
     through
    0.40
    POSITIVE LOGITS
    manı
    0.55
    자는
    0.46
    ת
    0.46
    ском
    0.46
    자에
    0.45
    자의
    0.45
    дзе
    0.45
    maktadır
    0.44
    संचार
    0.44
    мам
    0.44
    Activations Density 0.002%

    No Known Activations