© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 294
    Prev
    Next
    INDEX
    Explanations

    personal declarations and actions

    np_acts-logits-general · gemini-2.5-flash-lite

    proper nouns followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    م
    0.24
     orbitals
    0.23
     உள்ளன
    0.23
     ০
    0.22
     spaw
    0.22
     단위
    0.22
     gzip
    0.22
     *
    0.21
     qubit
    0.21
     ohm
    0.21
    POSITIVE LOGITS
     himself
    0.40
     resigned
    0.34
     pleaded
    0.33
     berkata
    0.32
     lamented
    0.32
     vowed
    0.31
     confessed
    0.31
     vehemently
    0.31
     personally
    0.30
     tweeted
    0.30
    Activations Density 1.047%

    No Known Activations