© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186734
    Prev
    Next
    INDEX
    Explanations

    We followed by a verb

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

    included or excluded

    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
     money
    0.52
    )
    0.48
     پیسہ
    0.48
     gate
    0.45
     y
    0.44
     away
    0.44
    0.44
     nervous
    0.43
     marketer
    0.43
     voltage
    0.43
    POSITIVE LOGITS
     จำ
    0.60
    يز
    0.54
    нтэр
    0.52
    ヴァ
    0.49
    ቷ
    0.48
    Ⴊ
    0.47
    žia
    0.47
     intervened
    0.46
     أيضاً
    0.46
    ллі
    0.46
    Activations Density 0.001%

    No Known Activations