© 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. 187933
    Prev
    Next
    INDEX
    Explanations

    professional design terms

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

    advice and states of being

    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
    ات
    0.57
    ত
    0.55
    ೆ
    0.54
    코
    0.54
    то
    0.51
    ون
    0.51
    קה
    0.51
    ת
    0.50
    コ
    0.50
    添
    0.50
    POSITIVE LOGITS
    architect
    0.51
     künstler
    0.50
     एलि
    0.45
     архі
    0.41
     फांसी
    0.41
     arquitect
    0.41
     AIDS
    0.40
     архи
    0.40
     került
    0.40
     മാത്രമല്ല
    0.40
    Activations Density 0.001%

    No Known Activations