© 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. 27337
    Prev
    Next
    INDEX
    Explanations

    because human, the peace

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

    specialized language

    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
     trin
    0.39
    undef
    0.38
    ವಾಸ
    0.38
     ಸ
    0.37
    \%
    0.36
     posisi
    0.35
     ylim
    0.35
     post
    0.35
    റിയ
    0.35
     quotient
    0.34
    POSITIVE LOGITS
    olt
    0.45
    耱
    0.41
    릭
    0.40
     রবীন্দ্রনাথ
    0.40
     sickening
    0.39
    LEY
    0.38
    Narrow
    0.38
    っているので
    0.38
    大家的
    0.38
    ത്സ
    0.37
    Activations Density 0.000%

    No Known Activations