© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 94971
    Prev
    Next
    INDEX
    Explanations

    specific word pairs

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

    how to write

    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
     Entscheid
    0.51
     bestehen
    0.47
     الشركات
    0.46
    irá
    0.45
    秃
    0.45
     золо
    0.44
     杨
    0.44
     భా
    0.44
     ክብ
    0.43
     பெரிய
    0.43
    POSITIVE LOGITS
    a
    0.45
    वाला
    0.44
     lecturer
    0.44
     campaigner
    0.44
    已经是
    0.44
    वर्स
    0.43
    Fight
    0.43
    NAN
    0.41
    վել
    0.41
     अलै
    0.40
    Activations Density 0.001%

    No Known Activations