© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    product descriptions; bandstand; mammography

    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
     from
    -0.88
    RTCK
    -0.87
     both
    -0.81
    RTSN
    -0.80
     sejarah
    -0.79
    ::{
    -0.79
     ingin
    -0.78
    と言って
    -0.76
    ždý
    -0.75
     escenario
    -0.74
    POSITIVE LOGITS
    ahora
    0.94
     psiqui
    0.93
    とろ
    0.92
     ZEALAND
    0.89
    Afghanistan
    0.88
     Ý
    0.86
    Argentina
    0.85
     Dakota
    0.85
    Übernach
    0.85
    uario
    0.84
    Activations Density 0.000%

    No Known Activations