© 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. 218520
    Prev
    Next
    INDEX
    Explanations

    machine or jaw crusher

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

    hair ties, timing, ruler, handshake, join

    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
     camin
    0.46
     drumming
    0.43
     irreg
    0.43
     গোয়
    0.43
    =-\
    0.43
    ⌐
    0.43
    
    0.42
     pessimism
    0.42
    ❸
    0.42
    
    0.42
    POSITIVE LOGITS
     انڈیا
    0.44
     gerçekten
    0.43
    posizione
    0.40
    ברים
    0.40
    способ
    0.40
    េរ
    0.40
    遼
    0.40
    icultural
    0.39
    destructive
    0.39
     lelaki
    0.39
    Activations Density 0.000%

    No Known Activations