© 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-262K
    7. 32290
    Prev
    Next
    INDEX
    Explanations

    a followed by adjective

    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_262k_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
     conjectured
    0.36
     sabbam
    0.33
    笪
    0.33
     člen
    0.32
     stev
    0.32
    有關
    0.31
     bribes
    0.31
     penjumlahan
    0.31
    誣
    0.31
     homeomorphism
    0.31
    POSITIVE LOGITS
    BER
    0.36
    aw
    0.35
     I
    0.34
    ab
    0.34
    ae
    0.34
    he
    0.34
    am
    0.33
    br
    0.32
    ung
    0.32
    ack
    0.32
    Activations Density 0.058%

    No Known Activations