© 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. 72622
    Prev
    Next
    INDEX
    Explanations

    destined or doomed

    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
    虓
    -2.53
    ޏ
    -2.45
     télévisée
    -2.45
    葙
    -2.39
    ࿊
    -2.36
    멩
    -2.34
     indépendant
    -2.27
    🢐
    -2.25
     ';
    -2.22
    ről
    -2.17
    POSITIVE LOGITS
     destined
    2.66
    ’
    2.50
    in
    2.39
     was
    2.31
    an
    2.30
    '
    2.16
     That
    2.11
    li
    2.00
    o
    2.00
    "
    1.96
    Activations Density 0.002%

    No Known Activations