© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44639
    Prev
    Next
    INDEX
    Explanations

    accidental or unintentional actions

    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
     király
    -1.40
     чтобы
    -1.27
     is
    -1.27
                
    -1.26
    い
    -1.25
     számára
    -1.20
    isateur
    -1.17
    Winner
    -1.16
    </h5>
    -1.15
     و
    -1.15
    POSITIVE LOGITS
     accidentally
    1.58
     accidental
    1.41
     inadvertently
    1.37
    Accidental
    1.36
    ന്റെ
    1.35
     ανθρώ
    1.34
    證明
    1.30
    nitten
    1.30
     several
    1.23
     sulla
    1.23
    Activations Density 0.032%

    No Known Activations