© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74594
    Prev
    Next
    INDEX
    Explanations

    Names followed by last names or context

    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
    '
    -3.41
    s
    -2.98
    ."
    -2.31
    “
    -2.27
    ing
    -2.25
    ଝ
    -2.14
    1
    -2.06
    
    -2.03
     With
    -2.02
     WITH
    -2.02
    POSITIVE LOGITS
     Kontexten
    2.64
     rápidos
    2.52
     mogą
    2.52
     zweifel
    2.48
     weitgehend
    2.44
    </h4>
    2.44
    曏
    2.42
    푦
    2.42
    }
    
    2.41
    ');
    2.36
    Activations Density 0.003%

    No Known Activations