© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    device identifiers

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

    keywords followed by common phrases

    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
    StarService
    0.58
     காவிரி
    0.48
     prosecution
    0.46
     Defts
    0.46
    โร
    0.46
     putative
    0.45
    myData
    0.44
    ;*/
    0.44
    DateField
    0.44
    Ꮀ
    0.44
    POSITIVE LOGITS
     to
    0.56
     n
    0.53
    imbing
    0.52
    to
    0.51
     bộ
    0.51
    踽
    0.50
     шабло
    0.49
     cách
    0.49
     Colle
    0.48
     нерав
    0.48
    Activations Density 0.000%

    No Known Activations