© 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. 82402
    Prev
    Next
    INDEX
    Explanations

    a, in, is, Two, Luis, /*, Progress, Q

    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
    拂
    -0.81
    ativität
    -0.74
    ediatric
    -0.73
    tiska
    -0.73
    Passer
    -0.72
    毂
    -0.71
    カチ
    -0.71
    Absor
    -0.71
    Pollution
    -0.70
     पुर
    -0.69
    POSITIVE LOGITS
    蹤
    0.82
     effects
    0.76
     unwilling
    0.75
     kondisi
    0.75
    igurumi
    0.74
     outdoors
    0.73
     creatures
    0.72
    坦
    0.70
    ย
    0.70
    oid
    0.69
    Activations Density 0.029%

    No Known Activations