© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9775
    Prev
    Next
    INDEX
    Explanations

    gain access

    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
     belangrijk
    -1.94
     it
    -1.78
     Then
    -1.75
    𓋼
    -1.74
     gorą
    -1.66
    猻
    -1.63
    end
    -1.63
    }$
    -1.62
    呓
    -1.61
     Это
    -1.59
    POSITIVE LOGITS
    genodigd
    2.14
    ኧ
    1.84
    (!__
    1.80
    pendente
    1.77
    geſ
    1.75
    dzić
    1.73
     där
    1.73
     rid
    1.63
     first
    1.61
    犼
    1.60
    Activations Density 0.021%

    No Known Activations