© 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. 15554
    Prev
    Next
    INDEX
    Explanations

    ... and punctuation

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

    numbers and then ellipses

    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
    軺
    0.52
     సన్ని
    0.39
    Drama
    0.39
     poderes
    0.38
    आईआर
    0.38
    轺
    0.38
     ছাপ
    0.38
    udarstven
    0.38
    bym
    0.37
     రాజ్యం
    0.37
    POSITIVE LOGITS
     …
    0.66
     ...
    0.57
     ….
    0.51
     \...
    0.49
     …..
    0.48
    ⁣
    0.47
     …”
    0.47
     …….
    0.45
     …,
    0.45
     ..
    0.44
    Activations Density 0.020%

    No Known Activations