© 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. 210597
    Prev
    Next
    INDEX
    Explanations

    florist example, Reserved Tax

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

    refugees destination dream deploy 5

    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
     Golpe
    0.53
     doloribus
    0.50
     gson
    0.48
     xAxis
    0.47
    废
    0.47
    𝄞
    0.47
    toolStripButton
    0.47
    லாம்
    0.46
     লিখেছেন
    0.46
     canción
    0.46
    POSITIVE LOGITS
    Authority
    0.46
     شامل
    0.43
    Se
    0.42
    andel
    0.42
    umo
    0.42
    Perform
    0.41
    DET
    0.41
    ally
    0.41
     Extremely
    0.41
     T
    0.41
    Activations Density 0.000%

    No Known Activations