© 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. 128979
    Prev
    Next
    INDEX
    Explanations

    earned or landed something

    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
     to
    -1.70
     what
    -1.53
     like
    -1.31
    ↵
    -1.30
    amerikanischer
    -1.29
     $
    -1.28
     whereas
    -1.28
     }
    -1.27
    louis
    -1.16
    ⎆
    -1.16
    POSITIVE LOGITS
     you
    2.08
     him
    1.77
     階段
    1.66
     появится
    1.54
     them
    1.44
    merate
    1.42
    さらに
    1.41
    ⍳
    1.41
     dimentic
    1.40
    苤
    1.39
    Activations Density 0.022%

    No Known Activations