© 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. 62435
    Prev
    Next
    INDEX
    Explanations

    multilingual word contexts

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

    foreign languages and scripts

    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
     presiden
    0.53
     presidencial
    0.45
    🗳
    0.45
     babe
    0.43
     Miro
    0.43
     leaf
    0.42
     paralel
    0.42
     geotechnical
    0.42
    ]^{-
    0.41
     tecn
    0.41
    POSITIVE LOGITS
    大きさ
    0.45
    েরি
    0.44
    இந்திய
    0.44
     velič
    0.42
    চল
    0.42
    puls
    0.41
    gx
    0.41
    ভাত
    0.40
    ні
    0.40
    важа
    0.40
    Activations Density 0.000%

    No Known Activations