© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    printing output with arguments

    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
    é
    0.45
    ;
    0.44
    ess
    0.44
     :
    0.42
     divulg
    0.42
     +\
    0.42
    are
    0.41
     procédés
    0.41
    pin
    0.41
    ję
    0.41
    POSITIVE LOGITS
    他
    0.52
    هن
    0.51
    隔離
    0.49
    ("#
    0.48
     "*************
    0.46
     gestionar
    0.46
    軾
    0.45
    ент
    0.44
    Chào
    0.44
    ("'
    0.44
    Activations Density 0.000%

    No Known Activations