© 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. 48363
    Prev
    Next
    INDEX
    Explanations

    origin or consequence

    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
    during
    -1.44
    髪の
    -1.34
     Periode
    -1.30
    𓇼
    -1.30
    ließen
    -1.30
    ErrUnexpectedEOF
    -1.28
     ilyen
    -1.25
    ````
    -1.24
    ोर्ट
    -1.24
     garan
    -1.21
    POSITIVE LOGITS
     that
    1.81
     about
    1.44
    ？！”
    1.31
    </em>
    1.31
     from
    1.24
    1
    1.23
    Want
    1.20
     then
    1.20
     both
    1.19
     premise
    1.19
    Activations Density 0.057%

    No Known Activations