© 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. 15029
    Prev
    Next
    INDEX
    Explanations

    cannot, insufficient, too, only

    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
     Qaraldi
    -0.98
     նաև
    -0.90
     erstmals
    -0.88
     ursprünglich
    -0.87
    今でも
    -0.85
    issent
    -0.85
     REFUND
    -0.84
    ⊑
    -0.84
    ographia
    -0.82
    WindowConstants
    -0.82
    POSITIVE LOGITS
     too
    1.43
     слишком
    1.22
     option
    1.09
    だけでは
    1.06
     only
    1.02
     cannot
    1.02
     can
    1.02
     demasiado
    1.01
     insufficient
    0.97
    するには
    0.96
    Activations Density 0.243%

    No Known Activations