© 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. 10-GEMMASCOPE-RES-131K
    4. 87186
    Prev
    Next
    INDEX
    Explanations

    identity crisis and theft

    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
    </em>
    -1.66
     the
    -1.53
     them
    -1.47
     said
    -1.29
     ボディ
    -1.28
    2
    -1.27
    ll
    -1.27
     recevrez
    -1.23
     AQUÍ
    -1.22
    才行
    -1.20
    POSITIVE LOGITS
    ્ય
    1.29
    Ꮉ
    1.28
    衎
    1.27
     !}
    1.27
    Также
    1.27
    vinfos
    1.25
    鞑
    1.24
    ;=
    1.23
     após
    1.22
     الباب
    1.21
    Activations Density 0.035%

    No Known Activations