© 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. 68057
    Prev
    Next
    INDEX
    Explanations

    not [adjective]

    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
     We
    -3.17
            
    -2.58
     There
    -2.30
     isn
    -2.28
    it
    -2.25
     From
    -2.22
    偲
    -2.19
     Does
    -2.14
     apolog
    -2.13
     n
    -2.08
    POSITIVE LOGITS
     weiße
    2.94
    塍
    2.86
    ⑊
    2.83
     grüne
    2.72
    biendo
    2.67
     ſeveral
    2.66
     juſt
    2.59
    ࣭
    2.55
    ཫ
    2.50
     blaue
    2.45
    Activations Density 0.073%

    No Known Activations