© 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. 21268
    Prev
    Next
    INDEX
    Explanations

    how to

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

    from the, gasp the, make

    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
     যেতে
    0.45
     RSW
    0.43
    cektir
    0.39
    வனம்
    0.39
    0.38
    -----
    0.38
    ------
    0.38
     ساک
    0.38
    ću
    0.38
    ---
    0.37
    POSITIVE LOGITS
    महा
    0.47
    圤
    0.41
    ޗ
    0.40
     conservar
    0.40
     Джей
    0.39
    㭜
    0.39
     scooters
    0.39
    鸬
    0.38
    ਟੀ
    0.38
     convenc
    0.38
    Activations Density 0.018%

    No Known Activations