© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16183
    Prev
    Next
    INDEX
    Explanations

    preposition of

    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_22/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
     any
    -1.83
     this
    -1.80
     their
    -1.73
     at
    -1.70
     its
    -1.68
     these
    -1.66
     every
    -1.41
     indah
    -1.39
    alló
    -1.37
     it
    -1.36
    POSITIVE LOGITS
     więc
    1.39
     zatem
    1.30
    '
    1.29
     ruhig
    1.21
    ज्ञ
    1.20
     verbessert
    1.15
    -
    1.14
     alguns
    1.11
     algunas
    1.11
    也不
    1.10
    Activations Density 0.107%

    No Known Activations