© 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. 118832
    Prev
    Next
    INDEX
    Explanations

    opening of lists and sections

    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
     that
    -1.23
     endDate
    -1.09
    pecting
    -1.05
    langkah
    -1.05
    ₱
    -1.02
     information
    -1.01
     but
    -1.01
    DataBind
    -0.99
    তথ্য
    -0.99
     säkert
    -0.96
    POSITIVE LOGITS
    <strong>
    1.55
     şun
    1.41
    inerario
    1.41
    <b>
    1.38
     seguenti
    1.29
    Kdo
    1.27
    arbonato
    1.25
     stärker
    1.21
    Legende
    1.18
     respira
    1.13
    Activations Density 0.177%

    No Known Activations