© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 240536
    Prev
    Next
    INDEX
    Explanations

    incidental or consequential

    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
    on
    0.56
    en
    0.54
    ed
    0.53
    ]){
    0.53
     from
    0.52
     on
    0.51
    та
    0.50
    ],
    0.50
    ক
    0.50
    к
    0.49
    POSITIVE LOGITS
     Yên
    0.45
     Cerr
    0.44
    ವುದ
    0.44
    कर्मा
    0.43
     epicenter
    0.42
     Pai
    0.42
     plume
    0.42
     tailgate
    0.42
     Lâm
    0.41
     Cheat
    0.41
    Activations Density 0.001%

    No Known Activations