© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59058
    Prev
    Next
    INDEX
    Explanations

    mainly including

    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
     on
    -2.05
     only
    -1.52
     and
    -1.52
     after
    -1.48
    </h2>
    -1.30
    v
    -1.29
     during
    -1.29
     within
    -1.28
     with
    -1.25
    ate
    -1.24
    POSITIVE LOGITS
     aparentemente
    1.68
    ⮑
    1.54
     armados
    1.52
     cette
    1.45
     obviamente
    1.41
    ICIENCY
    1.40
     its
    1.40
     problém
    1.40
     intéressant
    1.38
    鰯
    1.38
    Activations Density 0.608%

    No Known Activations