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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8063
    Prev
    Next
    INDEX
    Explanations

    days except Fridays

    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
     खरीदा
    -1.02
    "{\
    -0.94
    PRNewswire
    -0.93
    unzione
    -0.91
     hadn
    -0.88
    ({
    
    -0.88
     sequel
    -0.88
    }}{\
    -0.88
    $,
    -0.87
    meaux
    -0.86
    POSITIVE LOGITS
     except
    1.59
     Closed
    1.55
     closed
    1.52
    Closed
    1.48
    closed
    1.47
     excep
    1.36
     exceptions
    1.30
    except
    1.27
     CLOSED
    1.23
     véhic
    1.21
    Activations Density 0.015%

    No Known Activations