© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48155
    Prev
    Next
    INDEX
    Explanations

    allegedly, supposedly, purportedly, rumored

    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
    gyz
    -0.87
     arguably
    -0.77
     merah
    -0.76
    ēc
    -0.76
    ktor
    -0.75
     lakukan
    -0.74
     konkret
    -0.72
    venser
    -0.71
     nghĩ
    -0.71
    Publication
    -0.70
    POSITIVE LOGITS
     apparently
    1.80
    apparently
    1.64
     Apparently
    1.56
     мол
    1.54
    Apparently
    1.47
     says
    1.25
     said
    1.25
     according
    1.16
    parently
    1.16
     paraît
    1.15
    Activations Density 0.006%

    No Known Activations