© 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. 5903
    Prev
    Next
    INDEX
    Explanations

    ways to describe directions

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

    need a little information

    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
    Essa
    0.39
    સ
    0.38
    В
    0.38
    Questo
    0.37
    Difficult
    0.36
    कर
    0.36
    回应
    0.36
    新たな
    0.36
    ക
    0.36
    गण
    0.35
    POSITIVE LOGITS
     VERY
    0.53
     خیلی
    0.53
     praticamente
    0.53
     கிட்டத்தட்ட
    0.52
     hampir
    0.51
     মোটামুটি
    0.51
     거의
    0.49
     veldig
    0.49
     কমপক্ষে
    0.48
     almost
    0.48
    Activations Density 0.045%

    No Known Activations