© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    noun followed by conjunction or preposition

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

    generating scale

    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
    ↵↵
    0.61
    0.61
    ac
    0.54
    マ
    0.50
    …
    0.50
    core
    0.48
     Website
    0.48
    4
    0.47
     …
    0.47
    ↵
    0.46
    POSITIVE LOGITS
     рэгістра
    0.66
     paralysie
    0.66
     problemi
    0.64
     OBSERV
    0.64
     immunoblot
    0.64
     obserw
    0.64
     convexe
    0.61
     problemy
    0.61
     pengetahuan
    0.61
     sintomas
    0.61
    Activations Density 0.000%

    No Known Activations