© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90721
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
     THIRD
    -0.79
    }}_
    -0.76
     Ngoài
    -0.74
    控
    -0.71
     based
    -0.70
     tattered
    -0.69
    طع
    -0.69
    jenigen
    -0.69
     hello
    -0.69
    fahrens
    -0.69
    POSITIVE LOGITS
    WY
    1.13
    WT
    1.11
     GT
    1.02
     WY
    1.02
    ndrome
    1.00
    wt
    0.98
     acronym
    0.95
    YMMV
    0.94
    FY
    0.92
    GTG
    0.92
    Activations Density 0.046%

    No Known Activations