© 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. 103069
    Prev
    Next
    INDEX
    Explanations

    people starting with C

    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
    cannot
    -0.93
    count
    -0.90
    '".
    -0.88
     perro
    -0.82
    covered
    -0.81
    click
    -0.81
    美子
    -0.79
    筲
    -0.78
    corn
    -0.77
     hashlib
    -0.75
    POSITIVE LOGITS
     c
    1.32
     C
    1.30
     CJ
    1.28
     CQ
    1.26
     CSU
    1.23
     CZ
    1.23
     CBE
    1.22
     Cs
    1.20
     CDP
    1.20
     CSA
    1.20
    Activations Density 0.059%

    No Known Activations