© 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. 16374
    Prev
    Next
    INDEX
    Explanations

    preposition in

    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
    to
    -4.88
    an
    -3.48
    2
    -3.45
    and
    -3.02
    :
    -2.98
    a
    -2.89
    W
    -2.88
    7
    -2.86
    6
    -2.81
    -
    -2.80
    POSITIVE LOGITS
    
    2.67
    潆
    2.47
    遄
    2.39
    ⃙
    2.38
    櫺
    2.36
    🤐
    2.36
    跸
    2.34
    🗿
    2.30
    liſh
    2.20
    ᠲ
    2.20
    Activations Density 0.078%

    No Known Activations