© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204602
    Prev
    Next
    INDEX
    Explanations

    deliciously menacing

    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_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
     Undang
    0.46
     Yukon
    0.44
    =&
    0.42
    胍
    0.40
     SPECT
    0.39
     Andaman
    0.39
     TREND
    0.39
     Dirty
    0.39
     Yin
    0.39
     disso
    0.38
    POSITIVE LOGITS
    ിച്ചത്
    0.42
    estimators
    0.39
    ucco
    0.39
    akar
    0.37
     ਵਿ
    0.37
     menurunkan
    0.37
    舝
    0.37
    ěr
    0.36
     lut
    0.36
    硋
    0.36
    Activations Density 0.001%

    No Known Activations