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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 525
    Prev
    Next
    INDEX
    Explanations

    the + unique role or position

    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
    ."
    -1.70
     itself
    -1.66
    onViewCreated
    -1.62
    絎
    -1.59
    äiv
    -1.55
     irgendwie
    -1.49
     its
    -1.48
     any
    -1.48
    CurtirCurtir
    -1.47
    rvats
    -1.46
    POSITIVE LOGITS
     bleek
    1.49
    recent
    1.45
    following
    1.44
    😱
    1.44
    </h2>
    1.43
    often
    1.42
     fêtes
    1.42
    romeda
    1.41
    狆
    1.38
    }
    1.37
    Activations Density 0.033%

    No Known Activations