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. 8125
    Prev
    Next
    INDEX
    Explanations

    embedded object

    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
     he
    -1.09
     diputados
    -0.98
    핌
    -0.92
    MLA
    -0.89
     mere
    -0.88
    Σε
    -0.88
    否则
    -0.85
    瓩
    -0.85
     same
    -0.85
    uParam
    -0.84
    POSITIVE LOGITS
    DED
    0.98
     Emb
    0.95
    𖥧
    0.90
    𝙻
    0.89
     стал
    0.89
     iklan
    0.85
    </strong>
    0.85
    tk
    0.84
    颦
    0.82
    哽
    0.81
    Activations Density 0.024%

    No Known Activations