© 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. 69263
    Prev
    Next
    INDEX
    Explanations

    who said or thought

    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
     what
    -1.70
     using
    -1.59
     without
    -1.51
    WebControls
    -1.35
    袂
    -1.34
     after
    -1.32
    ляет
    -1.32
    )))),
    -1.29
    だったが
    -1.23
    antMatchers
    -1.23
    POSITIVE LOGITS
    ↵↵
    1.60
    1
    1.49
    ens
    1.48
    ons
    1.38
     Ahnung
    1.37
    をする
    1.34
    on
    1.27
     autorità
    1.24
    5
    1.23
     diesen
    1.23
    Activations Density 0.005%

    No Known Activations