© 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. 62894
    Prev
    Next
    INDEX
    Explanations

    states and conditions

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

    multi-lingual connectors

    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
     אשר
    0.36
     б
    0.35
     curt
    0.35
    либо
    0.34
    Raven
    0.34
    PC
    0.32
    ㄱ
    0.32
     ㄱ
    0.32
    ！！！！
    0.32
    Ｔ
    0.31
    POSITIVE LOGITS
     جلوگیری
    0.43
     पली
    0.42
    頑張
    0.39
     jalan
    0.38
     lucha
    0.37
    yness
    0.37
    iness
    0.37
     ਅਤੇ
    0.37
     gagal
    0.36
    နဲ့
    0.36
    Activations Density 0.001%

    No Known Activations