© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118052
    Prev
    Next
    INDEX
    Explanations

    acting via

    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_34/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
    getStore
    -0.82
    crema
    -0.75
     Rasulullah
    -0.72
    SignUp
    -0.71
    reado
    -0.70
    ութ
    -0.70
    catalogo
    -0.69
    tarte
    -0.69
    Navbar
    -0.69
     répartition
    -0.68
    POSITIVE LOGITS
    desde
    0.68
    pom
    0.66
    jø
    0.66
    zić
    0.65
    ivis
    0.65
    aras
    0.65
    chet
    0.64
    두
    0.64
    jor
    0.63
    lord
    0.63
    Activations Density 0.051%

    No Known Activations