© 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. 235841
    Prev
    Next
    INDEX
    Explanations

    common English words followed by nouns

    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
     Krank
    0.54
     Mö
    0.51
    1
    0.50
     Howe
    0.49
     Khan
    0.49
     Mitchell
    0.49
     Khy
    0.48
     Moss
    0.47
     Pike
    0.47
     Huan
    0.47
    POSITIVE LOGITS
    èges
    0.45
     semplicemente
    0.44
     appartiennent
    0.44
     impon
    0.43
     participer
    0.43
    즐
    0.43
     propriétaires
    0.42
     treas
    0.42
    아가
    0.42
     esperando
    0.41
    Activations Density 0.000%

    No Known Activations