© 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. 206231
    Prev
    Next
    INDEX
    Explanations

    collocated word pairs

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

    collecting pebbles, meticulously planning

    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
     சதவீ
    0.47
    édition
    0.47
     அனுமதிக்க
    0.45
     ஏதாவது
    0.44
    െയി
    0.44
    та
    0.44
    了吧
    0.44
    ፐ
    0.43
     сни
    0.43
    compens
    0.43
    POSITIVE LOGITS
     biodegrad
    0.47
     OI
    0.46
     ecosystems
    0.44
     anions
    0.44
     oy
    0.43
     referrals
    0.43
     oxalic
    0.43
     маник
    0.42
     unspoken
    0.42
     FH
    0.42
    Activations Density 0.002%

    No Known Activations