© 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. 127484
    Prev
    Next
    INDEX
    Explanations

    publication titles and years

    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
     after
    -1.46
     it
    -1.44
    ･･･
    -1.31
     There
    -1.31
    這是
    -1.27
    𓂅
    -1.24
     iaitu
    -1.23
     späteren
    -1.22
    كانت
    -1.20
    ítése
    -1.20
    POSITIVE LOGITS
     rése
    1.32
     süt
    1.29
     récemment
    1.26
    -&
    1.26
     aktual
    1.23
    她就
    1.23
     a
    1.19
     directamente
    1.18
    relation
    1.17
    recent
    1.16
    Activations Density 0.100%

    No Known Activations