© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60613
    Prev
    Next
    INDEX
    Explanations

    wasn't followed by temporal or circumstantial descriptor

    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_10/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
    떳
    -2.97
    鉨
    -2.92
    archiwizowane
    -2.88
    뿅
    -2.77
     finne
    -2.77
    俛
    -2.70
    懨
    -2.69
    臯
    -2.67
     間取り
    -2.59
    และ
    -2.58
    POSITIVE LOGITS
    </h1>
    3.09
     –
    3.06
    </i>
    2.72
    t
    2.69
    <i>
    2.66
    ↵
    2.64
     “[
    2.63
     
    2.63
    на
    2.55
     “
    2.41
    Activations Density 0.013%

    No Known Activations