© 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. 73555
    Prev
    Next
    INDEX
    Explanations

    dll path, Doc type, resource list

    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
    🦴
    -0.94
    hols
    -0.93
    merzen
    -0.91
    äher
    -0.90
    ᵊ
    -0.88
    கம்
    -0.88
    verige
    -0.88
    Île
    -0.86
    ството
    -0.84
     szint
    -0.84
    POSITIVE LOGITS
    ฯ
    1.00
    g
    0.86
    開設
    0.85
    T
    0.84
     different
    0.84
    m
    0.82
    <b>
    0.81
    E
    0.81
     keterangan
    0.80
    いくつかの
    0.79
    Activations Density 0.184%

    No Known Activations