© 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. 60451
    Prev
    Next
    INDEX
    Explanations

    related to treatments

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

    scarcity and limited availability

    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
    .​
    0.54
    umuz
    0.45
     disobedience
    0.45
    .}~\
    0.44
    .…
    0.42
     monasteries
    0.42
     hứng
    0.42
     dynasties
    0.42
    ​.
    0.41
     intoxication
    0.41
    POSITIVE LOGITS
    檸
    0.46
     Digit
    0.45
    鋰
    0.44
    Brid
    0.43
    redos
    0.43
    Tas
    0.42
    楨
    0.42
     डिजिट
    0.41
     Rep
    0.41
    odi
    0.41
    Activations Density 0.000%

    No Known Activations