© 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. 37857
    Prev
    Next
    INDEX
    Explanations

    sent, choice, settlement, record

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

    images as input

    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
     blissful
    0.48
    )}$,
    0.45
    வா
    0.44
    に至
    0.43
    geführt
    0.42
     splendid
    0.42
    мата
    0.42
    就已经
    0.41
     정의역
    0.41
    渡
    0.41
    POSITIVE LOGITS
     embaixo
    0.50
     bailar
    0.50
     menos
    0.48
     hydrogens
    0.48
     atletas
    0.48
     endoc
    0.47
     linha
    0.47
     hidrógeno
    0.46
     ули
    0.46
     átomos
    0.46
    Activations Density 0.000%

    No Known Activations