© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69245
    Prev
    Next
    INDEX
    Explanations

    Geographical and proper names

    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_22/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
    اااا
    -1.07
     of
    -1.06
     who
    -1.05
    opheles
    -1.02
     halus
    -1.02
     which
    -1.01
     которая
    -1.01
     transparan
    -1.00
     !!}
    -1.00
     now
    -0.98
    POSITIVE LOGITS
    ствуют
    1.05
    わけです
    1.04
    WITHOUT
    1.02
    久し
    1.02
     attestation
    1.00
    捽
    1.00
    感じで
    1.00
    muz
    1.00
     Recre
    0.95
     soñ
    0.95
    Activations Density 0.000%

    No Known Activations