© 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. 99958
    Prev
    Next
    INDEX
    Explanations

    X on Y constructions

    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
     when
    -1.51
     they
    -1.38
    ſſen
    -1.35
    悫
    -1.34
     ""
    -1.34
     "",
    -1.32
     ;
    -1.30
    铪
    -1.30
     skool
    -1.30
    ことができ
    -1.30
    POSITIVE LOGITS
    panasonic
    1.38
     with
    1.30
    おめでとう
    1.27
    場は
    1.25
     your
    1.25
    lichung
    1.24
     traditionally
    1.24
     troubled
    1.22
    Tout
    1.22
    tedy
    1.21
    Activations Density 0.084%

    No Known Activations