Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8437
    Prev
    Next
    INDEX
    Explanations

    numbers and non-latin script

    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
     arguably
    -0.92
     at
    -0.90
     even
    -0.89
     give
    -0.88
     time
    -0.86
     make
    -0.85
     showed
    -0.85
    mə
    -0.84
    zná
    -0.84
     create
    -0.83
    POSITIVE LOGITS
    oule
    0.90
     ;-
    0.89
     hébergement
    0.84
     occuper
    0.83
     dovr
    0.82
    兩
    0.82
     triom
    0.82
     espaces
    0.81
    औ
    0.81
     garantir
    0.81
    Activations Density 0.012%

    No Known Activations