© 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. 95410
    Prev
    Next
    INDEX
    Explanations

    personal information

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

    application submission

    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
     stash
    0.40
     second
    0.36
     holster
    0.36
     legit
    0.35
     fucking
    0.35
    מ
    0.35
     jackets
    0.34
    פע
    0.34
     sneaker
    0.33
     jacket
    0.33
    POSITIVE LOGITS
     लोकांना
    0.35
     сельскохозяй
    0.35
    amingo
    0.33
     تاہم
    0.32
     биологи
    0.31
     войск
    0.31
     растений
    0.30
    膳
    0.30
     повре
    0.30
    鬘
    0.30
    Activations Density 0.114%

    No Known Activations