© 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. 109761
    Prev
    Next
    INDEX
    Explanations

    side of

    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
    .
    -1.22
    1
    -1.11
     extraordinarily
    -1.07
     profoundly
    -1.05
     severely
    -1.05
     intensely
    -1.03
     irrespective
    -1.02
     highly
    -1.00
     solely
    -0.99
     allow
    -0.97
    POSITIVE LOGITS
     of
    1.54
     robuste
    1.33
     industrie
    1.33
    廂
    1.32
     français
    1.27
    ของ
    1.25
    lobe
    1.23
     praktis
    1.20
     kredi
    1.20
    براير
    1.19
    Activations Density 0.033%

    No Known Activations