© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38508
    Prev
    Next
    INDEX
    Explanations

    words that start sentences

    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
     行き
    -1.44
    皝
    -1.41
    ఝ
    -1.38
     Fuerzas
    -1.37
    鱚
    -1.36
    adalah
    -1.29
    joj
    -1.28
    okkal
    -1.27
    ङ
    -1.27
    お世話
    -1.26
    POSITIVE LOGITS
     also
    1.82
    H
    1.46
    !
    1.45
    P
    1.44
     is
    1.41
     "
    1.41
    t
    1.38
    d
    1.35
    r
    1.33
     in
    1.30
    Activations Density 0.092%

    No Known Activations