© 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. 209920
    Prev
    Next
    INDEX
    Explanations

    betweenorterm

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

    temporal cloak, micro SaaS, rac, PLAN, arch linux

    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
    䀘
    0.51
    aparikkh
    0.49
    ſh
    0.48
     detección
    0.47
    ທ
    0.46
     ಬಹು
    0.46
    çok
    0.46
     ஒத்து
    0.44
    극한
    0.44
    锞
    0.43
    POSITIVE LOGITS
    als
    0.52
    iles
    0.51
    ics
    0.48
    /
    0.48
    igg
    0.48
    oles
    0.48
    icky
    0.46
     Headlines
    0.46
    ivity
    0.45
     bans
    0.45
    Activations Density 0.002%

    No Known Activations