© 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. 209733
    Prev
    Next
    INDEX
    Explanations

    ending period

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

    visual explanations and coordinated action

    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
    the
    0.54
     the
    0.51
    ”
    0.51
    ?
    0.50
    8
    0.48
    :
    0.46
    rist
    0.46
    Т
    0.45
    9
    0.45
    .
    0.44
    POSITIVE LOGITS
    হইল
    0.49
     চৈতন্য
    0.48
    了很多
    0.47
    ম্ত
    0.45
    羡慕
    0.44
    handedly
    0.44
    फ्ते
    0.43
    她在
    0.43
    រស
    0.43
    냈다
    0.43
    Activations Density 0.000%

    No Known Activations