© 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. 34-GEMMASCOPE-RES-131K
    7. 64348
    Prev
    Next
    INDEX
    Explanations

    starting an action

    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_34/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
     possible
    -1.55
     still
    -1.52
     continue
    -1.40
     любить
    -1.40
     acestea
    -1.34
    上がった
    -1.28
     continuation
    -1.27
     likely
    -1.23
    悩む
    -1.23
     reduction
    -1.22
    POSITIVE LOGITS
     to
    1.47
     orchestr
    1.43
     giving
    1.23
     Menjadi
    1.19
     using
    1.18
     being
    1.16
    なのですが
    1.14
     making
    1.11
     {},
    1.05
    –
    1.05
    Activations Density 0.046%

    No Known Activations