© 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. 22-GEMMASCOPE-RES-131K
    7. 64996
    Prev
    Next
    INDEX
    Explanations

    removing from collections

    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_22/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
    しかし
    -0.94
    Finanz
    -0.84
     даже
    -0.82
    Stopped
    -0.82
    WriteBarrier
    -0.82
     już
    -0.82
    那麼
    -0.82
    觔
    -0.80
    umacher
    -0.79
     इसलिए
    -0.78
    POSITIVE LOGITS
     from
    1.45
     who
    1.01
    "]:
    1.00
     portátiles
    0.97
     of
    0.97
     vrijdag
    0.97
    ")))
    0.93
    kệ
    0.92
     removal
    0.91
     yesterday
    0.91
    Activations Density 0.004%

    No Known Activations