© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164327
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    `]]` followed by code comments

    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_262k_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
    Our
    0.53
    Models
    0.50
    Emma
    0.50
    Ⓡ
    0.49
    Science
    0.48
    Howard
    0.48
    Prot
    0.46
    大
    0.46
     Ö
    0.46
    Paul
    0.46
    POSITIVE LOGITS
     разные
    0.44
    бин
    0.43
     potro
    0.43
    мер
    0.43
    변경
    0.43
     cigar
    0.43
    рки
    0.42
    차가
    0.41
     AGS
    0.41
    급
    0.41
    Activations Density 0.000%

    No Known Activations