© 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. 72748
    Prev
    Next
    INDEX
    Explanations

    Swedish words and library names

    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
    €”
    -1.08
    providedIn
    -1.02
    <eos>
    -1.01
    useNewUrlParser
    -0.93
     same
    -0.92
    lios
    -0.91
    ority
    -0.89
     głó
    -0.89
    ditionally
    -0.88
    OrCreate
    -0.88
    POSITIVE LOGITS
    ↵
    0.96
     gånger
    0.93
    ↵↵
    0.92
     varmt
    0.92
    ,
    0.91
    Ekster
    0.90
    Dü
    0.90
     Imma
    0.90
     egens
    0.90
    ?");
    0.88
    Activations Density 0.016%

    No Known Activations