© 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. 8074
    Prev
    Next
    INDEX
    Explanations

    Manifest configuration files

    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
    眎
    -3.45
    ⸰
    -3.11
    縢
    -3.06
    หรือ
    -2.94
    缯
    -2.80
    埽
    -2.78
    gucig
    -2.69
    actéristi
    -2.66
    ѣмъ
    -2.58
    鵙
    -2.58
    POSITIVE LOGITS
    Usually
    3.13
    Surprisingly
    3.00
    It
    2.98
    During
    2.92
    Nearly
    2.92
    Most
    2.89
    Just
    2.84
    Since
    2.78
    While
    2.70
    Going
    2.70
    Activations Density 0.004%

    No Known Activations