© 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. 103053
    Prev
    Next
    INDEX
    Explanations

    URL patterns and code identifiers

    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
     cantora
    -0.77
     ribbon
    -0.73
    quim
    -0.73
     schließt
    -0.71
     ordini
    -0.71
     intercom
    -0.70
    siyon
    -0.70
    壺
    -0.68
    いえば
    -0.68
     Autoren
    -0.68
    POSITIVE LOGITS
     Dublin
    1.00
    rights
    0.90
     ECTS
    0.88
     qualifié
    0.87
    Dublin
    0.83
    zył
    0.77
    ѱ
    0.75
    oureuse
    0.75
    řej
    0.74
     }}>
    0.73
    Activations Density 0.024%

    No Known Activations