© 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. 10-GEMMASCOPE-RES-131K
    7. 70464
    Prev
    Next
    INDEX
    Explanations

    have you / a / the / such / been

    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
    윽
    -1.59
    gió
    -1.55
    有多少
    -1.51
    ciun
    -1.48
     relentlessly
    -1.47
    喟
    -1.46
    曲目
    -1.45
    ,“
    -1.45
    Ꮙ
    -1.44
    tiglie
    -1.42
    POSITIVE LOGITS
     améli
    1.59
    omorphism
    1.53
    known
    1.52
    cinogenicity
    1.47
    means
    1.40
    并且
    1.39
     renfor
    1.39
    ore
    1.39
    ture
    1.38
     a
    1.38
    Activations Density 0.018%

    No Known Activations