© 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. 55201
    Prev
    Next
    INDEX
    Explanations

    four other

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

    dashed when, Theron remembered, harmony, architecture, magical plants

    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
    めっちゃ
    0.47
    டி
    0.45
    applique
    0.43
    ўным
    0.43
    APPS
    0.43
    Skew
    0.43
    厛
    0.42
    巴巴
    0.42
     மட்டுமல்ல
    0.42
    DMA
    0.42
    POSITIVE LOGITS
    0.45
     tr
    0.39
     uur
    0.39
     olymp
    0.39
     \
    0.39
     excuses
    0.38
     tere
    0.38
    \
    0.38
              
    0.38
     MEM
    0.37
    Activations Density 0.000%

    No Known Activations