© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    type of city

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

    lists including numbers

    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
     didn
    0.61
    f
    0.56
     we
    0.55
    ia
    0.55
    ce
    0.53
    z
    0.50
     doesn
    0.49
     You
    0.48
    you
    0.47
    我
    0.47
    POSITIVE LOGITS
     bestimm
    0.58
     Straßen
    0.56
    ügel
    0.52
     ყ
    0.52
    杷
    0.51
     Doppel
    0.50
     Rücken
    0.50
     offenbar
    0.50
     تعیین
    0.49
    splitLength
    0.49
    Activations Density 0.001%

    No Known Activations