© 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. 34-GEMMASCOPE-RES-131K
    7. 93531
    Prev
    Next
    INDEX
    Explanations

    following along with

    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
     around
    -1.16
    を行い
    -1.09
    Along
    -1.03
     out
    -1.02
     away
    -1.01
    んですが
    -0.96
     this
    -0.96
    𝟑
    -0.95
     introduit
    -0.95
    哪裡
    -0.95
    POSITIVE LOGITS
     in
    1.32
    耵
    1.06
    쓸
    1.04
     скриншот
    0.99
     herbes
    0.98
     juſt
    0.94
    ohol
    0.92
     brillantes
    0.91
    桫
    0.91
     riscos
    0.90
    Activations Density 0.021%

    No Known Activations