© 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. 51912
    Prev
    Next
    INDEX
    Explanations

    this behaviour

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

    alternate realities and grammar

    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
     Gefühl
    0.53
     அதன்
    0.51
     своем
    0.49
    焓
    0.47
    ตัวเอง
    0.46
     форм
    0.46
     wrinkled
    0.46
     собственные
    0.46
    窿
    0.45
     interwoven
    0.45
    POSITIVE LOGITS
    スピ
    0.46
     भूटान
    0.45
     internazionali
    0.43
    sustaining
    0.42
     spain
    0.42
    Finland
    0.41
     shipment
    0.41
    checklist
    0.41
    alanine
    0.40
    international
    0.40
    Activations Density 0.000%

    No Known Activations