© 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. 160901
    Prev
    Next
    INDEX
    Explanations

    different choices, prior to, not deliberately

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

    multiple series or OR clauses

    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
    4
    0.51
    1
    0.50
    PSW
    0.49
    GS
    0.47
    No
    0.47
    Containers
    0.47
    containers
    0.47
    PW
    0.46
    5
    0.46
    RAF
    0.45
    POSITIVE LOGITS
     След
    0.55
    л
    0.54
    ன்
    0.52
     रूसी
    0.52
     ReLU
    0.52
     शरद
    0.52
     Cous
    0.50
     Mecklenburg
    0.50
     Tú
    0.49
    𝑡
    0.48
    Activations Density 0.000%

    No Known Activations