© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4029
    Prev
    Next
    INDEX
    Explanations

    actions and performance

    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
    ভৌম
    0.37
    飯店
    0.36
    𝟰
    0.34
    电压
    0.33
    宿泊
    0.33
     ขวด
    0.32
    ཧ
    0.32
    𝟯
    0.32
    binicons
    0.32
    ্ঠ
    0.32
    POSITIVE LOGITS
     Interactive
    0.46
     DIY
    0.45
     interactive
    0.44
     Contractors
    0.43
     actively
    0.42
     Active
    0.41
     Activities
    0.40
     активно
    0.39
     Cognitive
    0.39
     melakukan
    0.39
    Activations Density 0.211%

    No Known Activations