© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53108
    Prev
    Next
    INDEX
    Explanations

    small cats

    np_acts-logits-general · gemini-2.5-flash-lite

    who will doBusiness CapabilitiesScope Creepappear lessprotests were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Entrenamiento
    0.52
    碰
    0.45
    羮
    0.45
     Donnie
    0.45
     Saddle
    0.43
     Bump
    0.43
     temprano
    0.43
     Hoping
    0.42
     supremely
    0.42
    嘗試
    0.42
    POSITIVE LOGITS
     fisheries
    0.52
     payment
    0.48
     production
    0.47
    netflix
    0.47
    iol
    0.45
     railway
    0.45
    Ø
    0.45
     quarto
    0.45
     uprav
    0.45
     spatial
    0.45
    Activations Density 0.000%

    No Known Activations