© 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. 186172
    Prev
    Next
    INDEX
    Explanations

    stages and states

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

    database, simulated reality, missing, learn BIM

    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
     рассмотре
    0.48
    ări
    0.40
    єкт
    0.40
    ផង
    0.39
    ņem
    0.39
    叐
    0.38
     informativo
    0.38
    istico
    0.38
    আমাকে
    0.38
     synergistic
    0.38
    POSITIVE LOGITS
     seul
    0.46
     Ansatz
    0.46
     -
    0.45
     instead
    0.44
    M
    0.44
    ',
    0.43
     ("
    0.41
     congel
    0.41
    }{
    0.41
     ١
    0.41
    Activations Density 0.001%

    No Known Activations