© 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. 158909
    Prev
    Next
    INDEX
    Explanations

    choosing a lawyer for separation or practice

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

    boundary layer

    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
    reward
    0.51
    Reward
    0.48
    Ihr
    0.47
    wrapped
    0.46
    ш
    0.46
    Spiel
    0.45
    among
    0.45
    appreci
    0.45
    testimon
    0.44
    ч
    0.44
    POSITIVE LOGITS
     இருப்பதால்
    0.52
     plán
    0.52
     પરંતુ
    0.48
     deoarece
    0.48
     repos
    0.47
     porque
    0.46
    ूंकि
    0.45
     เพราะ
    0.45
     projets
    0.45
     planos
    0.44
    Activations Density 0.001%

    No Known Activations