© 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. 31-GEMMASCOPE-2-RES-262K
    7. 91568
    Prev
    Next
    INDEX
    Explanations

    topics and contexts

    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_31_width_262k_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
     unglaublich
    0.45
     Veränder
    0.44
     և
    0.43
     Polymers
    0.40
     föränd
    0.40
     Physiological
    0.39
     getCurrent
    0.39
     verändert
    0.39
    Dylan
    0.38
    实在是
    0.37
    POSITIVE LOGITS
    keywords
    0.44
    economy
    0.44
    )\
    0.43
     સલા
    0.42
    :}
    0.42
    ^\
    0.41
    被害
    0.41
    রিত
    0.40
     unimportant
    0.40
    のも
    0.38
    Activations Density 0.011%

    No Known Activations