© 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. 173659
    Prev
    Next
    INDEX
    Explanations

    actions or consequences

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

    HIGHLIGHTING sections and WALKS

    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
    撃
    0.46
    Ǘ
    0.45
     ਜ਼
    0.45
    Proto
    0.44
    WU
    0.43
    Figure
    0.43
    ophys
    0.42
    Ciudad
    0.42
    観
    0.42
    ธอ
    0.42
    POSITIVE LOGITS
     documenting
    0.55
     sections
    0.54
     overtook
    0.53
     motivating
    0.50
     alright
    0.49
     documented
    0.49
     Huntingdon
    0.48
     Tayler
    0.48
     section
    0.47
     researching
    0.46
    Activations Density 0.001%

    No Known Activations