© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11286
    Prev
    Next
    INDEX
    Explanations

    subjective atoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.40
    0.33
     At
    0.32
     ia
    0.31
     -
    0.30
     usar
    0.30
     usa
    0.29
     o
    0.29
     über
    0.29
     http
    0.28
    POSITIVE LOGITS
    த்தையும்
    0.34
    Asimismo
    0.32
    Saludo
    0.30
    Substring
    0.30
    DummyView
    0.29
    kében
    0.28
    Რ
    0.28
    Successful
    0.27
    வதற்காக
    0.27
    习近平
    0.27
    Activations Density 0.413%

    No Known Activations