© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13849
    Prev
    Next
    INDEX
    Explanations

    technology framework, US State, person who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     С
    0.39
     adherents
    0.37
     Induction
    0.37
     был
    0.37
     поиск
    0.36
     შეიძლება
    0.36
     он
    0.36
     tow
    0.35
    <sup>
    0.35
     आस
    0.35
    POSITIVE LOGITS
    disamb
    0.44
    عبة
    0.44
    啸
    0.44
    హ
    0.43
    ၾ
    0.43
    soort
    0.43
    codename
    0.42
     límite
    0.41
    嘯
    0.40
     loại
    0.40
    Activations Density 0.076%

    No Known Activations