© 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. 131097
    Prev
    Next
    INDEX
    Explanations

    future leaders

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

    style, asking, darkness, Maintaining

    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
    othiaz
    0.49
    ArgumentParser
    0.47
    र्ज
    0.46
     wir
    0.46
     MessageBox
    0.45
    ,%
    0.44
    ب
    0.44
     WAR
    0.43
    フォー
    0.43
     matlab
    0.42
    POSITIVE LOGITS
    вица
    0.55
    㨁
    0.53
    Necessary
    0.50
    欴
    0.49
    aise
    0.46
    способ
    0.46
    construct
    0.45
    needed
    0.45
    Спо
    0.44
     Спо
    0.44
    Activations Density 0.000%

    No Known Activations