© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92393
    Prev
    Next
    INDEX
    Explanations

    deserve

    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_34/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
     vedno
    -1.09
     približ
    -1.07
     interesar
    -1.03
    erenc
    -1.02
     stolet
    -1.01
    TRANSLATE
    -0.99
     vínculo
    -0.98
     Here
    -0.96
    利
    -0.96
    اضی
    -0.94
    POSITIVE LOGITS
     to
    1.27
    "
    1.12
    拥有
    1.10
     attention
    1.08
     être
    1.08
     consideration
    1.07
     being
    1.06
     называ
    1.05
     più
    1.03
     essere
    1.02
    Activations Density 0.010%

    No Known Activations