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. 8089
    Prev
    Next
    INDEX
    Explanations

    Red meat, Consumers desire, Scripture Formatting

    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
    Slime
    -0.94
    ጂ
    -0.94
     jute
    -0.91
    quadro
    -0.88
    !—
    -0.88
    Grat
    -0.88
    了许多
    -0.85
    ⤒
    -0.84
     Teaser
    -0.82
     tatsächlich
    -0.82
    POSITIVE LOGITS
    flutter
    1.16
    sprintf
    0.95
    了过来
    0.95
    googleapis
    0.91
    я
    0.91
    meta
    0.89
    })+\
    0.89
     nekem
    0.88
    }}_{\
    0.87
    噢
    0.87
    Activations Density 0.009%

    No Known Activations