© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    following the word not

    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
     Sometimes
    -1.63
     Some
    -1.52
     sami
    -1.40
     noté
    -1.35
     ideologies
    -1.27
                    
    -1.26
     deities
    -1.26
    ذت
    -1.26
    报记者
    -1.25
    每次
    -1.23
    POSITIVE LOGITS
    s
    1.41
    t
    1.41
    er
    1.41
    zione
    1.37
    ⩴
    1.35
    especially
    1.35
    اں
    1.34
    Certainly
    1.34
     weiteres
    1.33
     především
    1.33
    Activations Density 0.006%

    No Known Activations