© 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. 120612
    Prev
    Next
    INDEX
    Explanations

    design, which, wash, for, an, locker

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

    special topics and sequences

    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
    タニ
    0.53
     courtesy
    0.48
    следова
    0.47
    ści
    0.45
    azioni
    0.45
     $
    0.45
     local
    0.44
     none
    0.43
     rare
    0.43
     impermeable
    0.43
    POSITIVE LOGITS
     atthakath
    0.49
     verfügt
    0.46
    存放
    0.45
     verfü
    0.43
     desarrolla
    0.42
     раствора
    0.42
     landlab
    0.42
     wiederum
    0.42
    磡
    0.42
     reçoit
    0.41
    Activations Density 0.001%

    No Known Activations