© 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. 117303
    Prev
    Next
    INDEX
    Explanations

    time and structure

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

    language and code constructs

    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
     migr
    0.48
     pessimism
    0.47
     drift
    0.46
    מ
    0.46
    桎
    0.45
     catast
    0.45
     digoxin
    0.45
     DELLA
    0.45
     mammalian
    0.44
     canzone
    0.44
    POSITIVE LOGITS
    两天
    0.52
    ouchers
    0.47
    rawdę
    0.47
     săptăm
    0.47
     ១
    0.46
    ısından
    0.46
    ându
    0.45
     солнца
    0.45
     မြ
    0.45
    ễm
    0.44
    Activations Density 0.000%

    No Known Activations