© 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. 9689
    Prev
    Next
    INDEX
    Explanations

    made some choices

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

    list item descriptors

    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
    ،
    0.43
     interplay
    0.41
    、「
    0.40
     enanti
    0.40
     murine
    0.39
     varie
    0.39
     دیے
    0.39
    ྪ
    0.38
     parthenogenetic
    0.38
     spectral
    0.38
    POSITIVE LOGITS
     It
    0.67
    this
    0.63
    do
    0.59
     it
    0.59
    you
    0.56
    s
    0.55
    They
    0.55
     Luckily
    0.55
    that
    0.54
    it
    0.54
    Activations Density 0.599%

    No Known Activations