© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109705
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
     of
    -1.23
    Being
    -1.09
     Being
    -1.05
     as
    -1.02
     Sudah
    -1.02
     their
    -1.00
    Still
    -0.98
     són
    -0.96
     being
    -0.96
     from
    -0.94
    POSITIVE LOGITS
     pratiquer
    1.02
     augmenter
    0.94
    馓
    0.92
    dominant
    0.91
    isFirst
    0.90
     ltd
    0.89
     ordonn
    0.89
    Presenta
    0.88
    せっかく
    0.88
    Algérie
    0.87
    Activations Density 0.002%

    No Known Activations