© 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. 43918
    Prev
    Next
    INDEX
    Explanations

    associated the, expands on, cost of

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

    structure and composition

    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
     Boko
    0.46
     hammer
    0.46
     whatsapp
    0.45
    ้ว
    0.45
     AG
    0.44
    頓
    0.44
     гало
    0.43
     Betsy
    0.43
     banter
    0.42
     G
    0.42
    POSITIVE LOGITS
    composition
    0.50
    україн
    0.49
     संश्
    0.49
     Says
    0.46
    ап
    0.44
    struktur
    0.44
    cultural
    0.44
    缴纳
    0.43
     टिश्यू
    0.42
    chevron
    0.42
    Activations Density 0.000%

    No Known Activations