© 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. 143788
    Prev
    Next
    INDEX
    Explanations

    words starting with "che"

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

    check, cheque, cheat, chew, cheek

    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
     SSID
    0.54
    </h2>
    0.52
     DHCP
    0.50
    仯
    0.50
     IPTV
    0.49
     VoIP
    0.48
    फु
    0.47
     ISP
    0.46
     condenser
    0.46
    \%,
    0.46
    POSITIVE LOGITS
    CHE
    0.85
     cheque
    0.79
     チェック
    0.78
     чек
    0.76
    Che
    0.75
     chemo
    0.75
     チェ
    0.75
    CHECKS
    0.72
     CHE
    0.71
     checker
    0.71
    Activations Density 0.059%

    No Known Activations