© 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. 71889
    Prev
    Next
    INDEX
    Explanations

    Jewish and Indian religious texts

    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
     hacemos
    -1.28
     ******
    -1.23
    міні
    -1.14
    piegel
    -1.10
    zerű
    -1.09
    *
    -1.09
     who
    -1.08
    立刻
    -1.07
    ****
    -1.06
     تلاش
    -1.06
    POSITIVE LOGITS
     also
    1.36
     may
    1.33
     might
    1.27
    してた
    1.20
     également
    1.19
     dodatk
    1.18
    鈦
    1.10
     azzurro
    1.09
     prized
    1.09
     guidelines
    1.09
    Activations Density 0.035%

    No Known Activations