© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41690
    Prev
    Next
    INDEX
    Explanations

    voting and elections

    np_acts-logits-general · gemini-2.5-flash-lite

    unethical and harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ャ
    0.41
    트롤
    0.40
    연구
    0.40
     Artículo
    0.40
    Methylsulfanyl
    0.40
    욬
    0.40
    읽
    0.39
    幷
    0.39
     <*>
    0.39
     мәкалә
    0.39
    POSITIVE LOGITS
     interval
    0.48
     delayed
    0.46
     periode
    0.46
     Pour
    0.44
     gọn
    0.44
     E
    0.43
     placer
    0.43
    TA
    0.42
     reversed
    0.42
     deadline
    0.42
    Activations Density 0.000%

    No Known Activations