© 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. 153947
    Prev
    Next
    INDEX
    Explanations

    drug store purchase

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

    representing character length constraints

    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
    нят
    0.48
     उसकी
    0.47
    getNumber
    0.47
    )$\
    0.46
     الحكم
    0.46
     Subsection
    0.46
     ज्‍यादा
    0.46
     Normdatei
    0.46
    }}(\
    0.46
     Purnama
    0.46
    POSITIVE LOGITS
     linear
    0.54
     motors
    0.51
     pelvis
    0.51
     fours
    0.50
     silage
    0.49
     cylindrical
    0.49
     polycarbonate
    0.48
     glazing
    0.48
     steril
    0.47
     glaciers
    0.46
    Activations Density 0.002%

    No Known Activations