© 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. 156171
    Prev
    Next
    INDEX
    Explanations

    omitted because

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

    words about possession/completion/art/inclusion

    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
    コ
    0.55
    cepteur
    0.54
     Ко
    0.50
     Maradona
    0.50
    インパクト
    0.48
    ка
    0.47
    גו
    0.47
    𝚙
    0.47
     estrellas
    0.46
     estadounidenses
    0.46
    POSITIVE LOGITS
     bizony
    0.46
    وال
    0.46
    enced
    0.43
    ).—
    0.43
    วิธีการ
    0.43
     rhin
    0.42
    ต์
    0.41
    ส่วน
    0.40
     Rhin
    0.40
    plr
    0.40
    Activations Density 0.001%

    No Known Activations