© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    into/in/to phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    man
    -1.24
    up
    -1.18
    ries
    -1.13
    thing
    -1.09
    ily
    -1.09
    is
    -1.08
     gâ
    -1.07
    any
    -1.04
    ารถ
    -1.03
    ung
    -1.02
    POSITIVE LOGITS
     współpracy
    1.37
    zji
    1.25
     badań
    1.21
    ïti
    1.18
    ⁍
    1.16
    Donnerstag
    1.15
    .$,
    1.14
     выгод
    1.13
     posible
    1.09
    issors
    1.09
    Activations Density 0.093%

    No Known Activations