© 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. 210792
    Prev
    Next
    INDEX
    Explanations

    contextual phrases

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

    beyond sector, expired, Hungarian, early

    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
    жени
    0.48
    женного
    0.46
    ンドウ
    0.45
    她们
    0.45
    િ
    0.45
    анг
    0.44
    गिंग
    0.44
    ിലാണ്
    0.44
    ટે
    0.43
    鉆
    0.43
    POSITIVE LOGITS
    \
    0.48
     mögliche
    0.48
     září
    0.46
     kop
    0.46
    sharing
    0.44
     sikap
    0.43
     beim
    0.43
     brû
    0.43
    *}$
    0.43
     \
    0.43
    Activations Density 0.001%

    No Known Activations