© 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. 37884
    Prev
    Next
    INDEX
    Explanations

    namely, respectively, precisely

    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
    either
    -0.84
     bowiem
    -0.82
    indeed
    -0.80
    otherwise
    -0.77
     Benny
    -0.75
    both
    -0.74
    Ecc
    -0.72
    NewUser
    -0.71
     Ведь
    -0.71
     теперь
    -0.70
    POSITIVE LOGITS
     именно
    1.48
    ly
    1.35
     namely
    1.32
     zwar
    1.27
     mian
    1.14
     savoir
    1.10
    ately
    1.10
     Именно
    1.03
     precisely
    1.00
    tó
    0.99
    Activations Density 0.051%

    No Known Activations