© 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. 33706
    Prev
    Next
    INDEX
    Explanations

    my followed by a noun

    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
     is
    -3.20
    <bos>
    -2.88
     you
    -2.59
    🡺
    -2.19
    䊐
    -2.06
    enchymal
    -2.00
    zegovina
    -1.99
    quatch
    -1.99
     для
    -1.97
    ptonshire
    -1.97
    POSITIVE LOGITS
     own
    3.64
    They
    2.59
     boneco
    2.48
    先週
    2.36
     very
    2.31
     brinquedo
    2.30
    久しぶりの
    2.27
     relógio
    2.25
    昨日の
    2.20
     schlechte
    2.19
    Activations Density 0.129%

    No Known Activations