© 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. 118715
    Prev
    Next
    INDEX
    Explanations

    in accordance with

    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
     prevent
    -1.41
     (
    -1.41
    to
    -1.39
     potentially
    -1.30
     arguably
    -1.29
     where
    -1.27
    !!!!
    -1.23
    <b>
    -1.23
     fairly
    -1.23
     allow
    -1.22
    POSITIVE LOGITS
     accordance
    1.31
     issus
    1.30
     strategie
    1.25
    🗿
    1.24
    😐
    1.24
    鹪
    1.23
    ₩
    1.23
    wki
    1.23
    😑
    1.21
     welk
    1.20
    Activations Density 0.126%

    No Known Activations