© 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. 34-GEMMASCOPE-RES-131K
    4. 55609
    Prev
    Next
    INDEX
    Explanations

    compound phrases and named entities

    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
     widely
    -0.96
     enormously
    -0.94
     bereits
    -0.93
     Perhaps
    -0.93
     going
    -0.88
     Many
    -0.86
     many
    -0.86
     from
    -0.83
     garner
    -0.83
    lighed
    -0.82
    POSITIVE LOGITS
     Leica
    1.09
    rotz
    1.02
     Horizontal
    0.93
     фото
    0.93
    ⪧
    0.91
    ſſel
    0.91
     remarks
    0.91
    odetic
    0.90
    NOS
    0.89
     halte
    0.88
    Activations Density 0.000%

    No Known Activations