© 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. 22-GEMMASCOPE-RES-131K
    7. 65862
    Prev
    Next
    INDEX
    Explanations

    earned a Bachelor of Arts degree

    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_22/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
     choroby
    -1.41
     pomys
    -1.41
     entretenimiento
    -1.41
     testé
    -1.29
     jouets
    -1.27
     alojamientos
    -1.27
     equipamentos
    -1.26
    鷽
    -1.25
     brinquedos
    -1.24
     eenen
    -1.23
    POSITIVE LOGITS
     and
    1.42
     when
    1.39
     When
    1.29
     went
    1.27
     as
    1.27
     four
    1.23
     After
    1.19
     get
    1.18
     if
    1.18
     got
    1.16
    Activations Density 0.032%

    No Known Activations