© 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. 227822
    Prev
    Next
    INDEX
    Explanations

    different languages or specific vocabulary

    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
     Frankfurt
    0.52
     London
    0.52
     Berlin
    0.52
    之处
    0.51
     Freeway
    0.50
     Builds
    0.49
     Marseille
    0.47
    ],
    0.46
     Proposals
    0.46
     Oyster
    0.46
    POSITIVE LOGITS
    呪
    0.52
    жена
    0.51
    minas
    0.51
     ಕರಿ
    0.47
    抗菌
    0.46
     deacon
    0.46
     ಔಷ
    0.46
     medicamentos
    0.44
    ược
    0.44
     प्रोत्सा
    0.42
    Activations Density 0.001%

    No Known Activations