© 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. 99234
    Prev
    Next
    INDEX
    Explanations

    and such

    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
     and
    -1.82
     audiobooks
    -1.38
    ஸ்
    -1.36
    FERENCE
    -1.29
     freaking
    -1.28
     Vortrag
    -1.27
     perturbation
    -1.25
    cual
    -1.22
     R
    -1.21
    なぜ
    -1.20
    POSITIVE LOGITS
     olla
    1.56
    </em>
    1.55
    ޸
    1.38
    feira
    1.34
    ية
    1.34
    silien
    1.34
    onomy
    1.33
     предлага
    1.30
     vores
    1.29
    h
    1.29
    Activations Density 0.018%

    No Known Activations