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. 8436
    Prev
    Next
    INDEX
    Explanations

    risk factors

    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
     текста
    -1.03
    ?”
    -1.02
     interwoven
    -1.00
     cinto
    -0.99
     fostered
    -0.99
        
    -0.96
    ).”
    -0.95
    술
    -0.92
    In
    -0.91
     целом
    -0.91
    POSITIVE LOGITS
     of
    1.58
     factors
    1.47
    ier
    1.34
     factor
    1.31
    factors
    1.28
     assessment
    1.27
     Risk
    1.27
    risk
    1.23
     Factors
    1.20
     geldi
    1.17
    Activations Density 0.026%

    No Known Activations