© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9487
    Prev
    Next
    INDEX
    Explanations

    "Eiffel Tower", cat, sandwich, tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ឬ
    0.54
    หรือ
    0.51
     혹은
    0.51
    거나
    0.50
     qualités
    0.50
    あるいは
    0.49
     condições
    0.49
     किंवा
    0.48
     vérité
    0.47
    하거나
    0.47
    POSITIVE LOGITS
    ."
    0.50
    .”
    0.47
    2
    0.45
     Python
    0.44
     tablespoons
    0.43
    '
    0.42
     Außerdem
    0.42
     preprocessing
    0.41
    9
    0.40
    8
    0.40
    Activations Density 0.177%

    No Known Activations