© 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. 35345
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    specific labels followed by value

    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
     penggunaan
    0.45
    Clar
    0.44
    сно
    0.41
    пили
    0.40
     prestigio
    0.40
    פי
    0.39
     testAvg
    0.39
    피
    0.38
     использование
    0.38
     непосред
    0.38
    POSITIVE LOGITS
     ஆயிரம்
    0.47
     Boż
    0.46
     travaille
    0.46
     刺繍
    0.44
     merciless
    0.44
     ਯ
    0.44
     poz
    0.43
     Poz
    0.43
     അനുവദ
    0.43
     guère
    0.43
    Activations Density 0.000%

    No Known Activations