© 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. 150279
    Prev
    Next
    INDEX
    Explanations

    purchase

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

    wife, kissing, still, options

    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
     sont
    0.57
     dua
    0.50
    спек
    0.49
     selectors
    0.49
     u
    0.49
     iki
    0.48
     are
    0.47
     chag
    0.47
     increased
    0.47
     masuk
    0.47
    POSITIVE LOGITS
     פרו
    0.54
     መሳሪያ
    0.52
    IMPLEMENT
    0.51
    Participant
    0.51
     الدراسة
    0.47
     худо
    0.47
     κατά
    0.46
    <unused49>
    0.46
     účast
    0.45
    PROXY
    0.44
    Activations Density 0.001%

    No Known Activations