© 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. 56103
    Prev
    Next
    INDEX
    Explanations

    code generation, data structures

    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
    大さじ
    -0.68
     Abends
    -0.68
     Calab
    -0.67
    lerinden
    -0.67
     施設
    -0.67
     remains
    -0.66
     Nutzen
    -0.66
    ɡ
    -0.65
    ufort
    -0.65
     assemblies
    -0.64
    POSITIVE LOGITS
     игрушка
    0.72
    FEEDBACK
    0.71
    द्
    0.70
    ęło
    0.70
    athlon
    0.67
    反省
    0.66
    wige
    0.65
     Bose
    0.65
     говорят
    0.65
     berp
    0.64
    Activations Density 0.040%

    No Known Activations