© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84207
    Prev
    Next
    INDEX
    Explanations

    programming for loops

    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_10/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
    czerw
    -2.05
    sandalia
    -2.03
    rası
    -2.03
     obiec
    -2.00
    Välisling
    -1.96
     playas
    -1.94
    Ꮞ
    -1.93
    🎐
    -1.88
    Ꮠ
    -1.87
    Pendidikan
    -1.86
    POSITIVE LOGITS
    —
    2.42
    '
    2.41
    0
    2.31
    4
    2.20
    5
    2.19
    8
    2.17
    for
    2.17
    ....
    2.13
    7
    2.13
    9
    2.11
    Activations Density 0.043%

    No Known Activations