© 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. 50361
    Prev
    Next
    INDEX
    Explanations

    movement in and out

    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
     करके
    -0.71
    zeera
    -0.68
    込んだ
    -0.68
    گیر
    -0.67
    dup
    -0.66
     Linz
    -0.66
    eniu
    -0.66
    addLast
    -0.65
    Soc
    -0.65
     مه
    -0.65
    POSITIVE LOGITS
    InOut
    2.42
    出入
    2.00
    进
    1.80
    เข้า
    1.74
     进
    1.70
    inout
    1.67
     ingress
    1.60
     entering
    1.59
     entrando
    1.55
     entrar
    1.53
    Activations Density 0.077%

    No Known Activations