© 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. 72625
    Prev
    Next
    INDEX
    Explanations

    composition of, composition with

    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
    .
    -3.27
    <i>
    -2.48
     gebeten
    -2.33
    </i>
    -2.23
    We
    -2.14
    ísa
    -1.98
     vorbereitet
    -1.96
     begr
    -1.95
     gestartet
    -1.95
    This
    -1.92
    POSITIVE LOGITS
    ⢪
    2.56
    ୈ
    2.44
    剮
    2.28
     \
    2.19
     réputation
    2.14
     soeur
    2.13
     planète
    2.09
    枓
    2.06
    珦
    2.06
     белом
    2.05
    Activations Density 0.005%

    No Known Activations