© 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. 134154
    Prev
    Next
    INDEX
    Explanations

    activities and events

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

    DFS, Skills, and phrases like "absolutely"

    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
     unchanged
    0.40
     maximize
    0.39
     maximise
    0.39
     legitimate
    0.39
    ত্যার
    0.39
    탄
    0.38
     arma
    0.38
     aspirin
    0.38
     psychologically
    0.38
    प्ताहिक
    0.37
    POSITIVE LOGITS
    lide
    0.48
    l
    0.47
    erweise
    0.47
    לה
    0.46
    lán
    0.46
    tyn
    0.46
    burse
    0.45
    lah
    0.44
     దు
    0.44
    lal
    0.44
    Activations Density 0.001%

    No Known Activations