© 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. 51
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrast

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

    introducing categories or examples

    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
    ،
    0.30
    ,
    0.26
     ،
    0.22
    、
    0.21
     atoms
    0.19
     ؟
    0.19
    ፣
    0.19
     oxyd
    0.19
     ।
    0.19
     ,
    0.19
    POSITIVE LOGITS
     लेकिन
    0.28
    as
    0.27
    लेकिन
    0.26
    although
    0.25
    allowing
    0.25
    which
    0.25
    despite
    0.24
    providing
    0.24
     позволя
    0.24
    including
    0.24
    Activations Density 1.309%

    No Known Activations