© 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. 148816
    Prev
    Next
    INDEX
    Explanations

    currency exchange and values

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

    calculating direction or scaler

    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
    ʢ
    0.52
    ünüz
    0.49
     başladı
    0.49
     încep
    0.49
     lunes
    0.49
    |^{\
    0.47
    Ğ
    0.47
    fälle
    0.46
    ):=\
    0.46
    begin
    0.46
    POSITIVE LOGITS
     workable
    0.43
     convers
    0.42
     warranties
    0.41
     warranty
    0.41
     suitable
    0.40
     possibility
    0.39
    Citizen
    0.38
     அவனை
    0.38
     result
    0.38
     змо
    0.38
    Activations Density 0.000%

    No Known Activations