© 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. 10-GEMMASCOPE-RES-131K
    7. 8273
    Prev
    Next
    INDEX
    Explanations

    state or action after be

    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
     if
    -2.09
    If
    -1.82
     when
    -1.55
     continued
    -1.52
     якщо
    -1.51
    When
    -1.49
    Если
    -1.48
    ︓
    -1.46
     quién
    -1.41
    teig
    -1.41
    POSITIVE LOGITS
     zowel
    1.66
     about
    1.55
    らしいです
    1.42
     a
    1.40
     to
    1.39
     such
    1.39
     altså
    1.37
     also
    1.32
    はない
    1.32
    ではなく
    1.30
    Activations Density 0.039%

    No Known Activations