© 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. 36297
    Prev
    Next
    INDEX
    Explanations

    figures, decrypt, vaccines, haunting, magnet

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

    conditional control

    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
     be
    0.54
     is
    0.53
     or
    0.48
     are
    0.48
    s
    0.47
     favorit
    0.47
    t
    0.47
     adalah
    0.47
     the
    0.46
     هستند
    0.46
    POSITIVE LOGITS
    ຂອງ
    0.50
    OfInterest
    0.50
    ของการ
    0.49
    OfDeath
    0.47
     γλώ
    0.44
     болезни
    0.42
    Celltype
    0.42
    ীম
    0.41
    槭
    0.41
    丰富的
    0.40
    Activations Density 0.001%

    No Known Activations