© 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. 220761
    Prev
    Next
    INDEX
    Explanations

    tango, ©, angel, report, gadget

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

    this allows

    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
    しながら
    0.49
    рат
    0.46
     paced
    0.46
    させて
    0.45
     علاقه
    0.45
    赛事
    0.45
     рассказа
    0.45
    始
    0.45
     primos
    0.45
     paces
    0.44
    POSITIVE LOGITS
    UEN
    0.46
    UED
    0.46
    UDE
    0.46
    thememanager
    0.45
    FA
    0.43
    ILI
    0.42
    SED
    0.42
     silahkan
    0.42
    helicopter
    0.41
     您
    0.41
    Activations Density 0.000%

    No Known Activations