© 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. 21681
    Prev
    Next
    INDEX
    Explanations

    Michael and variations

    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
     보다
    0.40
     сле
    0.38
     보
    0.38
    보다
    0.37
     উই
    0.37
    보
    0.37
    々に
    0.36
     разли
    0.36
     lässt
    0.35
    세
    0.35
    POSITIVE LOGITS
    ਾਕ
    0.46
     impeding
    0.44
    Ⴉ
    0.42
    აცი
    0.41
     merciful
    0.40
     negotiators
    0.40
     micrograms
    0.40
    <0x8A>
    0.40
     michael
    0.40
     autocratic
    0.39
    Activations Density 0.003%

    No Known Activations