© 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. 25465
    Prev
    Next
    INDEX
    Explanations

    checking string containment

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

    checking existence or condition is met

    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
    永远
    0.52
    顺序
    0.45
    除非
    0.44
    垻
    0.44
    尽可能
    0.43
     যতদিন
    0.43
    ρο
    0.42
    聵
    0.40
    APPY
    0.40
    ानुसार
    0.40
    POSITIVE LOGITS
     yeter
    0.59
     suficiente
    0.53
     überhaupt
    0.53
     पर्याप्त
    0.53
     quelconque
    0.51
     genug
    0.48
     wirkt
    0.46
     gült
    0.46
     suficientes
    0.45
     sufficient
    0.45
    Activations Density 0.002%

    No Known Activations