© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77409
    Prev
    Next
    INDEX
    Explanations

    words preceded by specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     különböző
    -1.23
    ตัวเอง
    -1.20
    ıyorum
    -1.16
     dámské
    -1.13
     kateg
    -1.10
     verschillende
    -1.08
     dáms
    -1.07
     disagre
    -1.06
     nélkül
    -1.05
     desarrollo
    -1.02
    POSITIVE LOGITS
     gladly
    1.08
     abide
    1.05
     thrice
    1.03
     garnered
    0.99
     exceeding
    0.98
     manner
    0.98
     swift
    0.98
     tokens
    0.97
     secretly
    0.92
     swiftly
    0.92
    Activations Density 0.020%

    No Known Activations