© 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. 9954
    Prev
    Next
    INDEX
    Explanations

    group of

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

    group of

    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
    ك
    0.91
    ка
    0.73
    '}).
    0.65
    ↵
    0.64
    c
    0.62
    <0x80>
    0.61
    lə
    0.60
     l
    0.59
     can
    0.59
    to
    0.58
    POSITIVE LOGITS
     группы
    1.17
     групи
    1.15
     grupo
    1.13
     groups
    1.09
     nhóm
    1.05
     ομά
    1.02
     groupes
    1.02
     گروپ
    0.98
     grupos
    0.98
     gruppo
    0.97
    Activations Density 0.085%

    No Known Activations