© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11828
    Prev
    Next
    INDEX
    Explanations

    target, TARGET, rope, Log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     এরা
    0.39
     figlio
    0.37
     இறைவன்
    0.36
     அவர்
    0.35
    ണിത്
    0.34
     யார்
    0.34
    硕
    0.34
    initi
    0.34
    )((
    0.34
    nT
    0.33
    POSITIVE LOGITS
     нашем
    0.39
     нашего
    0.38
     vårt
    0.38
     naše
    0.36
     обозна
    0.36
     aforementioned
    0.36
    weichen
    0.35
     нанесе
    0.35
    ಿಕೆ
    0.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
    Activations Density 0.515%

    No Known Activations