© 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. 90519
    Prev
    Next
    INDEX
    Explanations

    finding WA

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

    applicable, message, inside, battery, results, flowing, Causes, papers, Requirements

    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
     rationale
    0.49
     genial
    0.49
    =`
    0.47
    eters
    0.44
    ot
    0.44
     nervousness
    0.44
    omens
    0.43
    릿
    0.42
    ost
    0.41
    oled
    0.40
    POSITIVE LOGITS
    دين
    0.50
     اسی
    0.45
    必ず
    0.45
    歙
    0.45
     பா
    0.44
     सम
    0.44
    ခ
    0.44
     必ず
    0.44
     जबर
    0.44
     upravo
    0.44
    Activations Density 0.000%

    No Known Activations