© 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. 89449
    Prev
    Next
    INDEX
    Explanations

    air ticket deals

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

    Clear intention

    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
    ت
    0.55
    cipline
    0.52
    t
    0.51
    I
    0.51
    ef
    0.50
    С
    0.50
    Т
    0.50
    त
    0.50
    us
    0.49
    י
    0.49
    POSITIVE LOGITS
     ಸುದ್ದಿ
    0.44
    汽
    0.43
     ಅದು
    0.43
     metas
    0.42
     Erfahr
    0.42
    ার্
    0.42
     ፍ
    0.41
    按钮
    0.41
     McCann
    0.41
     тера
    0.41
    Activations Density 0.001%

    No Known Activations