© 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. 198004
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    actions or intentions

    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
    CD
    0.60
    胱
    0.59
    片的
    0.53
    엷
    0.51
    Cinema
    0.51
    散射
    0.50
    
    0.49
    无穷
    0.48
    扰
    0.47
    CP
    0.46
    POSITIVE LOGITS
     I
    0.62
     funcion
    0.55
     former
    0.54
     decon
    0.53
     prime
    0.52
     ar
    0.52
     people
    0.52
     este
    0.51
     meu
    0.50
     Sh
    0.50
    Activations Density 0.000%

    No Known Activations