© 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. 11883
    Prev
    Next
    INDEX
    Explanations

    work and its context

    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
    ichtigung
    -0.96
     attravers
    -0.93
    empty
    -0.90
     prosegu
    -0.88
    Durch
    -0.88
     esplor
    -0.86
     pública
    -0.86
    Merge
    -0.86
     abbin
    -0.84
     déchir
    -0.83
    POSITIVE LOGITS
     on
    1.23
     according
    1.21
     for
    1.16
     with
    1.11
     hard
    1.07
     in
    0.97
    铃
    0.89
     upon
    0.88
     towards
    0.85
     prefeito
    0.84
    Activations Density 0.029%

    No Known Activations