© 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. 228195
    Prev
    Next
    INDEX
    Explanations

    phrases with prepositions

    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
    '
    0.61
    2
    0.55
     Caputo
    0.53
    сто
    0.48
    ᠴ
    0.47
    and
    0.46
     informed
    0.45
    ZY
    0.45
     ANTON
    0.45
    <0xE8>
    0.44
    POSITIVE LOGITS
    ousands
    0.46
    restriction
    0.44
     hoops
    0.42
    buckets
    0.42
    getPrice
    0.42
    发出
    0.42
    ，$
    0.41
     épaules
    0.41
    navigation
    0.41
     Má
    0.41
    Activations Density 0.000%

    No Known Activations