© 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. 257038
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cuya
    0.49
     Верхов
    0.46
     базе
    0.45
     ViewGroup
    0.44
     Пав
    0.44
     cláus
    0.43
    忝
    0.43
     क्यू
    0.42
     जिसमें
    0.42
     fearing
    0.42
    POSITIVE LOGITS
    yla
    0.50
    ITING
    0.47
    اه
    0.46
    ا
    0.45
    ه
    0.45
    silent
    0.44
    code
    0.44
    ewords
    0.44
    proble
    0.43
    produkte
    0.43
    Activations Density 0.005%

    No Known Activations