© 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. 102542
    Prev
    Next
    INDEX
    Explanations

    human and continuations

    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
    Aga
    -0.90
    eluaran
    -0.84
    カラー
    -0.84
     cuadrado
    -0.80
    ramientas
    -0.80
     så
    -0.80
    پیوند
    -0.79
    ং
    -0.79
     свои
    -0.79
    heber
    -0.78
    POSITIVE LOGITS
     beings
    2.30
    oids
    1.48
    human
    1.29
     Human
    1.24
     readable
    1.23
     human
    1.16
    race
    1.15
     interaction
    1.13
    sized
    1.13
    readable
    1.13
    Activations Density 0.047%

    No Known Activations