© 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. 3844
    Prev
    Next
    INDEX
    Explanations

    wet and saturated state

    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
    她
    -1.80
    j
    -1.79
    n
    -1.77
    al
    -1.76
    le
    -1.73
    琑
    -1.70
    r
    -1.70
    and
    -1.68
    他
    -1.66
    ad
    -1.63
    POSITIVE LOGITS
    沨
    2.00
    潆
    1.86
     ſame
    1.82
    colgante
    1.58
     generalmente
    1.58
    ínű
    1.56
    妧
    1.55
    教训
    1.51
     amenaz
    1.49
    extAlignment
    1.49
    Activations Density 0.010%

    No Known Activations