© 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. 41884
    Prev
    Next
    INDEX
    Explanations

    either, both, whichever

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

    choice or option

    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
    හ
    0.40
     surprising
    0.36
    ہرست
    0.36
     Chichester
    0.36
    otrop
    0.35
    霞
    0.35
    ވާ
    0.35
    िकुलम
    0.35
     Pann
    0.34
    啇
    0.34
    POSITIVE LOGITS
    どちら
    1.53
     whichever
    1.45
    いずれ
    1.33
    前者
    1.16
    ichever
    1.07
     begge
    1.04
    两者
    1.02
     Either
    0.98
     keduanya
    0.98
     beiden
    0.95
    Activations Density 0.146%

    No Known Activations