© 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. 59006
    Prev
    Next
    INDEX
    Explanations

    neither, nowhere, not, nobody

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

    interests directly, today

    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
    にて
    0.46
    የ
    0.45
    <0x0D>
    0.45
    Legal
    0.43
    Mach
    0.43
    รายการ
    0.42
    仕事
    0.42
    Q
    0.42
    insa
    0.42
    NS
    0.41
    POSITIVE LOGITS
     nadie
    0.59
     aucun
    0.51
     coexist
    0.50
     ninguna
    0.49
     niemand
    0.48
     ahora
    0.48
     ngayon
    0.47
     nessuno
    0.45
     今天
    0.45
     没有
    0.45
    Activations Density 0.000%

    No Known Activations