© 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. 222206
    Prev
    Next
    INDEX
    Explanations

    value and equality

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

    modules, nodes, locker, exercise, falling, swap

    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
    endorong
    0.50
     प्रक्षे
    0.47
     Faculté
    0.46
    pard
    0.45
    𝐤
    0.45
     무료
    0.43
    בע
    0.43
    kW
    0.43
    fraction
    0.43
     hỗn
    0.43
    POSITIVE LOGITS
     congruent
    0.45
     platform
    0.43
     piattaforma
    0.42
    ⮕
    0.42
     Platform
    0.42
     viu
    0.42
     uitvo
    0.42
    0.42
    ઈ
    0.41
     findings
    0.41
    Activations Density 0.000%

    No Known Activations