© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93385
    Prev
    Next
    INDEX
    Explanations

    long followed by description

    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
     briefly
    -1.04
     brief
    -0.91
     locaux
    -0.91
     larger
    -0.85
    のではなく
    -0.84
     commerciaux
    -0.83
     llanto
    -0.82
    birthDate
    -0.81
    monument
    -0.81
    dateOfBirth
    -0.81
    POSITIVE LOGITS
     (>
    1.69
     ago
    1.38
     LONG
    1.07
    titud
    1.05
    Long
    1.02
     طولانی
    1.01
    long
    1.01
     Long
    0.95
    (>
    0.94
    distance
    0.94
    Activations Density 0.051%

    No Known Activations