© 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. 67269
    Prev
    Next
    INDEX
    Explanations

    music playback and control

    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
    erski
    -1.23
    ⌝
    -1.22
     langs
    -1.20
     spécialiste
    -1.18
     हू
    -1.12
    Ꮳ
    -1.12
    ])){
    -1.10
     ceremon
    -1.09
     greeted
    -1.09
     TextInputType
    -1.09
    POSITIVE LOGITS
     on
    1.35
     this
    1.29
     where
    1.27
     each
    1.25
     only
    1.22
     contient
    1.21
    engkapnya
    1.20
    gypte
    1.17
     gustado
    1.16
     detuvo
    1.15
    Activations Density 0.073%

    No Known Activations