© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130201
    Prev
    Next
    INDEX
    Explanations

    not, only, just

    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
     („
    -0.84
     چنین
    -0.80
    ákat
    -0.80
    下列
    -0.80
     also
    -0.79
     الآخر
    -0.79
    Джерела
    -0.78
    However
    -0.77
     however
    -0.77
     nevertheless
    -0.76
    POSITIVE LOGITS
    不仅
    1.43
    不仅仅
    1.22
     not
    1.16
     already
    1.15
    不但
    1.13
     уже
    1.08
    不僅
    1.06
     değil
    1.05
    だけでなく
    1.05
     когда
    1.02
    Activations Density 0.042%

    No Known Activations