© 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. 43855
    Prev
    Next
    INDEX
    Explanations

    right, one, B, from

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

    features and benefits

    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
     Almeida
    0.54
    lut
    0.53
     Concepción
    0.51
    čku
    0.49
     Лон
    0.49
    \|
    0.47
     Ruk
    0.47
    čka
    0.46
     कोरबा
    0.46
     Lí
    0.46
    POSITIVE LOGITS
    
    0.47
     parametrized
    0.45
    ખ્ય
    0.44
     parametrization
    0.44
    शिक्षा
    0.44
    government
    0.44
    Parameterized
    0.43
    وینت
    0.42
    நிய
    0.42
     prosperous
    0.41
    Activations Density 0.000%

    No Known Activations