© 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. 159321
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    can could

    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
     tij
    0.50
    U
    0.44
    UO
    0.43
    ];
    0.42
     starved
    0.42
     bo
    0.41
     bò
    0.41
    Q
    0.41
    زيد
    0.41
     ij
    0.41
    POSITIVE LOGITS
     ही
    0.57
     มือ
    0.52
     फॉर
    0.50
     ہی
    0.49
     Allianz
    0.48
     pembelian
    0.47
     ऑन
    0.47
    पीरियंस
    0.47
     Primeira
    0.47
     आम्ही
    0.47
    Activations Density 0.000%

    No Known Activations