© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110507
    Prev
    Next
    INDEX
    Explanations

    introducing conditional clauses

    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
     normalerweise
    -1.35
     meistens
    -1.30
     vielfäl
    -1.29
     basically
    -1.29
     różne
    -1.27
    ที่จะ
    -1.26
    набор
    -1.26
     quindi
    -1.24
    ”،
    -1.23
     different
    -1.20
    POSITIVE LOGITS
    Alike
    1.40
     Francus
    1.25
    Semantics
    1.20
    Ź
    1.20
    १
    1.17
    ῾
    1.15
    Ĺ
    1.15
    身旁
    1.14
    providedIn
    1.13
     лишь
    1.12
    Activations Density 0.402%

    No Known Activations