© 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. 27666
    Prev
    Next
    INDEX
    Explanations

    different conditions

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

    "er" followed by "ick"

    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
     Filosof
    0.51
     फे
    0.47
    шава
    0.46
    Ard
    0.45
     ಅಲ
    0.45
     ミニ
    0.44
    重心
    0.44
    <unused74>
    0.43
    riamo
    0.43
     Gelände
    0.43
    POSITIVE LOGITS
     by
    0.55
     be
    0.53
    ன்கள்
    0.48
    произ
    0.47
    ль
    0.45
     declar
    0.44
     produzione
    0.43
    zą
    0.43
     produz
    0.42
    Ờ
    0.42
    Activations Density 0.000%

    No Known Activations