© 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. 200873
    Prev
    Next
    INDEX
    Explanations

    acquisitions

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

    resource management context

    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
    یک
    0.64
    یکشن
    0.54
     ১৯
    0.52
    ik
    0.49
     রবিবার
    0.48
    ▃
    0.48
    ১৯
    0.47
    十四
    0.45
    راً
    0.45
    ین
    0.44
    POSITIVE LOGITS
     minut
    0.48
     honeymoon
    0.47
     catchy
    0.46
     appar
    0.44
     Ри
    0.43
     defini
    0.42
     э
    0.42
     noten
    0.41
    也不会
    0.41
     dicht
    0.41
    Activations Density 0.000%

    No Known Activations