© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107083
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and assignments

    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
     niektor
    -1.02
     quitté
    -1.01
    わけではない
    -0.98
     לקבל
    -0.97
     borrar
    -0.96
     certaines
    -0.96
    になってしまう
    -0.96
    も良い
    -0.96
    になるので
    -0.95
     bazı
    -0.92
    POSITIVE LOGITS
     =
    3.50
    =
    2.86
    >=</
    2.28
    }=
    2.23
    }=\
    2.11
    }}=
    1.97
     }}=
    1.95
     }=\
    1.94
     = 
    1.86
     $=\
    1.84
    Activations Density 0.076%

    No Known Activations