© 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. 44199
    Prev
    Next
    INDEX
    Explanations

    how things work or make sense

    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
     alike
    -1.37
     praticamente
    -1.32
    ских
    -1.32
     frequentemente
    -1.28
     assister
    -1.24
     Weisheit
    -1.23
     Bisch
    -1.20
     remarkably
    -1.16
     materie
    -1.16
     extremely
    -1.16
    POSITIVE LOGITS
     logic
    1.30
     out
    1.26
    ),
    1.23
     argument
    1.23
     with
    1.16
     data
    1.14
    ”,
    1.14
     contradiction
    1.13
    },
    1.12
    U
    1.10
    Activations Density 0.051%

    No Known Activations