© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-16K
    4. 8530
    Prev
    Next
    INDEX
    Explanations

    conclusion, high, backend introductions

    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
     AGAIN
    0.49
    错误的
    0.43
    abhavam
    0.43
    рования
    0.42
     бекер
    0.41
    okban
    0.41
    𒌋
    0.40
     Μα
    0.39
     ಸಂಧಿ
    0.39
     Again
    0.39
    POSITIVE LOGITS
     hingegen
    0.51
     natomiast
    0.42
     counterpart
    0.39
     provides
    0.38
       
    0.36
    ,
    0.35
     cujo
    0.34
     can
    0.33
     comes
    0.33
     possesses
    0.33
    Activations Density 0.821%

    No Known Activations