© 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. 25367
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with 1

    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
    7
    -1.23
    0
    -1.10
     If
    -1.05
     *
    -1.05
    \\
    -1.00
     Berechnung
    -1.00
     diesen
    -0.98
     "
    -0.97
    5
    -0.97
     prachtige
    -0.96
    POSITIVE LOGITS
    //=
    1.34
    𝘛
    1.32
    狁
    1.30
     primeiros
    1.27
    ẨM
    1.26
     mapas
    1.25
    umerable
    1.25
     <=",
    1.24
    ➀
    1.22
     žád
    1.18
    Activations Density 0.041%

    No Known Activations