© 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. 149274
    Prev
    Next
    INDEX
    Explanations

    is in category

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

    fragile, sensitive, or challenged entities

    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
     सत्
    0.59
     создан
    0.48
     створе
    0.48
    霸
    0.47
     페
    0.46
    Trước
    0.46
    രായി
    0.46
     ಬ
    0.45
    ಸ
    0.45
     hoods
    0.45
    POSITIVE LOGITS
    repeat
    0.45
    Unique
    0.45
    шем
    0.43
    Changing
    0.43
     magnific
    0.42
    have
    0.42
    must
    0.41
    Hill
    0.41
     splend
    0.41
    glucose
    0.41
    Activations Density 0.000%

    No Known Activations