© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38201
    Prev
    Next
    INDEX
    Explanations

    home and abroad or past and present

    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
     in
    -1.59
     being
    -1.41
     other
    -1.41
     on
    -1.31
     when
    -1.30
     something
    -1.27
     gustaba
    -1.26
     gestire
    -1.23
     instead
    -1.21
    si
    -1.20
    POSITIVE LOGITS
     and
    6.56
    และ
    3.02
     maupun
    2.94
     AND
    2.67
    および
    2.36
     및
    2.27
     lẫn
    2.25
     и
    2.22
     \&
    2.11
     மற்றும்
    2.06
    Activations Density 0.237%

    No Known Activations