© 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. 22-GEMMASCOPE-RES-131K
    7. 95821
    Prev
    Next
    INDEX
    Explanations

    "Yeah" or "I" followed by personal statements

    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_22/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
     those
    -1.70
     these
    -1.62
     any
    -1.44
     with
    -1.38
     provide
    -1.30
     only
    -1.27
     some
    -1.24
     this
    -1.23
     make
    -1.21
     may
    -1.19
    POSITIVE LOGITS
    ответ
    1.16
    preferably
    1.14
    鸲
    1.12
     égard
    1.10
     bén
    1.10
    likte
    1.09
     étr
    1.09
    ఽ
    1.08
     femeninos
    1.08
    definitely
    1.07
    Activations Density 0.034%

    No Known Activations