© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24417
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and steps

    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
     accented
    0.44
     正
    0.36
    と呼ばれる
    0.36
    ঞ্জ
    0.35
    hotmail
    0.33
    anyi
    0.33
     amplified
    0.33
    ﭥ
    0.32
     cushioned
    0.32
     popularly
    0.32
    POSITIVE LOGITS
     этих
    0.37
    ذه
    0.35
     administratif
    0.34
    ll
    0.34
    ។
    0.34
     inim
    0.33
     પાસે
    0.33
     ADMINISTRATIVE
    0.33
    sterdam
    0.33
    তরে
    0.33
    Activations Density 0.056%

    No Known Activations