© 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. 80722
    Prev
    Next
    INDEX
    Explanations

    behavior and types

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

    consistent effort

    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
    ίζει
    0.49
    资产
    0.45
    ี
    0.45
    ])).
    0.44
    ייתה
    0.43
    ี้
    0.43
    ęż
    0.43
    اسية
    0.43
    ཥ
    0.43
    ไอ
    0.43
    POSITIVE LOGITS
     danced
    0.48
     Kindness
    0.46
     الاح
    0.45
    湆
    0.43
     manifestations
    0.42
     Resilience
    0.42
    MASTER
    0.42
     cérémonie
    0.42
     dances
    0.42
     neighborhoods
    0.42
    Activations Density 0.001%

    No Known Activations