© 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. 89009
    Prev
    Next
    INDEX
    Explanations

    complete description

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

    these will

    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
    ]{\
    0.49
     الم
    0.48
     العديد
    0.48
    ٩
    0.48
     أبريل
    0.48
     تلاميذ
    0.48
     التلاميذ
    0.47
     ಹಲವಾರು
    0.47
    ِه
    0.46
     جوړونکي
    0.46
    POSITIVE LOGITS
    Susp
    0.46
     supp
    0.44
    ってます
    0.43
    全部
    0.43
     restent
    0.42
    枧
    0.42
    常规
    0.42
     fut
    0.42
    cessing
    0.41
    Ratio
    0.41
    Activations Density 0.000%

    No Known Activations