© 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. 91530
    Prev
    Next
    INDEX
    Explanations

    other, more, tracking, suitcases

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

    hidden, resistant, known, CSPRNG, resynthesis

    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
     dyed
    0.49
     ngữ
    0.47
    mathscr
    0.46
    らなかった
    0.46
     jazy
    0.45
    flies
    0.45
    鑣
    0.45
    ?:
    0.45
    ية
    0.44
     dye
    0.44
    POSITIVE LOGITS
    зидента
    0.46
     Emir
    0.46
    ของการ
    0.43
     coinciding
    0.42
    dengan
    0.42
     ਯ
    0.42
     ketua
    0.42
     ਅਤੇ
    0.41
    이브
    0.40
     Gyne
    0.40
    Activations Density 0.001%

    No Known Activations