© 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. 118923
    Prev
    Next
    INDEX
    Explanations

    Android/Java contexts

    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
     here
    -2.75
    here
    -1.82
     aquí
    -1.74
    Here
    -1.62
     здесь
    -1.60
     اینجا
    -1.53
     tutaj
    -1.49
     Here
    -1.49
     HERE
    -1.48
    在这里
    -1.45
    POSITIVE LOGITS
     there
    1.19
     these
    1.07
     context
    1.00
    ればいい
    0.86
     getContext
    0.85
     öffnungszeiten
    0.83
    يوب
    0.82
    nościo
    0.81
    這些
    0.80
     cucchiai
    0.79
    Activations Density 0.007%

    No Known Activations