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. 8100
    Prev
    Next
    INDEX
    Explanations

    business and investment holdings

    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
     racconta
    -0.92
     рекоменду
    -0.80
     appartamento
    -0.80
     setempat
    -0.79
     chiede
    -0.78
    bbene
    -0.78
     рекомен
    -0.76
     potrebbe
    -0.74
     来自
    -0.74
    윤
    -0.73
    POSITIVE LOGITS
     investments
    1.93
     ventures
    1.52
     hotels
    1.46
     hotel
    1.43
     investment
    1.34
     holdings
    1.34
    hotel
    1.29
    holdings
    1.23
    invest
    1.21
     stakes
    1.21
    Activations Density 0.064%

    No Known Activations