© 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. 182652
    Prev
    Next
    INDEX
    Explanations

    we may

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

    building dreams and goals

    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
    0.54
    mse
    0.49
     इत्यादी
    0.49
    其他
    0.48
    业绩
    0.48
    я
    0.46
    ాలను
    0.45
    SelectItem
    0.45
    ാത്ത
    0.45
    ("^
    0.45
    POSITIVE LOGITS
    raphic
    0.51
     modelling
    0.49
     tracking
    0.48
    '
    0.48
     sufficiently
    0.47
     pulsed
    0.47
     normed
    0.46
     dynamism
    0.45
     watchlist
    0.44
     vectorized
    0.43
    Activations Density 0.000%

    No Known Activations