Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12061
    Prev
    Next
    INDEX
    Explanations

    company name descriptors

    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_22/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
     embaraz
    -1.49
    衚
    -1.41
     helicópter
    -1.40
    Bé
    -1.39
     repuesto
    -1.38
     ПРЕ
    -1.37
    をしました
    -1.36
     hilfre
    -1.36
    angkap
    -1.35
     oído
    -1.34
    POSITIVE LOGITS
    co
    1.72
    z
    1.70
    w
    1.66
    q
    1.64
    h
    1.56
    f
    1.56
     also
    1.55
    v
    1.55
    n
    1.53
    ll
    1.52
    Activations Density 0.046%

    No Known Activations