© 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. 137732
    Prev
    Next
    INDEX
    Explanations

    work, images, segment, item, win

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

    these later, each stage, any other

    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
    Methylsulfanyl
    0.48
     Malk
    0.46
    érir
    0.45
     ګرځ
    0.45
    鶯
    0.45
     brah
    0.44
     انگری
    0.44
     Верх
    0.44
    wString
    0.43
    󠁢
    0.43
    POSITIVE LOGITS
    IPv
    0.45
    товый
    0.45
    ారం
    0.45
    Threads
    0.45
    INE
    0.43
     threads
    0.43
    VIDOR
    0.43
    IDAD
    0.42
    +
    0.42
    EC
    0.42
    Activations Density 0.000%

    No Known Activations