© 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. 195756
    Prev
    Next
    INDEX
    Explanations

    connecting words and phrases

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

    classic question

    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
    します
    0.47
     formulas
    0.46
     hect
    0.45
    t
    0.45
     chaotic
    0.44
     rn
    0.44
     thang
    0.44
     secretaries
    0.44
     discret
    0.42
     scanners
    0.42
    POSITIVE LOGITS
     घोष
    0.52
    铒
    0.52
    ittances
    0.52
     встреча
    0.51
    ки
    0.50
     हैव
    0.49
    צו
    0.48
     শীর্ষে
    0.48
     سبب
    0.47
    warf
    0.47
    Activations Density 0.002%

    No Known Activations