© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15608
    Prev
    Next
    INDEX
    Explanations

    product color descriptions

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

    carry out

    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_16k_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
    ̬
    0.42
     amin
    0.37
    ल्डेन
    0.36
     guessed
    0.36
     पहल
    0.36
    aminase
    0.35
     deduce
    0.35
    amicin
    0.35
    antera
    0.35
    itable
    0.34
    POSITIVE LOGITS
    ത്തിറ
    0.35
     "$(
    0.34
    іо
    0.34
     مخاط
    0.34
    ग्राम
    0.33
     شہریوں
    0.33
     پروف
    0.33
    тат
    0.33
     (:
    0.32
     موسم
    0.32
    Activations Density 0.050%

    No Known Activations