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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118868
    Prev
    Next
    INDEX
    Explanations

    numerical values and money

    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
    _
    -2.63
                    
    -2.38
    is
    -2.22
    mathrm
    -2.20
    and
    -2.09
    It
    -2.06
    </strong>
    -2.02
     أيضاً
    -1.98
    he
    -1.92
    ll
    -1.88
    POSITIVE LOGITS
     this
    1.94
    靫
    1.86
    .'
    1.71
    capai
    1.71
    jelasan
    1.70
    +'.
    1.70
    ⒎
    1.69
    dersfield
    1.68
     some
    1.66
    鹛
    1.61
    Activations Density 0.033%

    No Known Activations