© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144340
    Prev
    Next
    INDEX
    Explanations

    Each Consumer

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

    necessity and requirements

    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
    Negative Logits
    ec
    0.46
    irk
    0.45
    unction
    0.45
    als
    0.44
    was
    0.44
    randint
    0.42
    ~~~~~~~~
    0.42
    (
    0.42
    ies
    0.41
     t
    0.40
    POSITIVE LOGITS
     dhinak
    0.54
    蟎
    0.52
     poderão
    0.50
     njemu
    0.50
    ریان
    0.50
     neko
    0.50
    اہر
    0.49
     potranno
    0.49
     śmierci
    0.48
    盹
    0.48
    Activations Density 0.002%

    No Known Activations