© 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. 234964
    Prev
    Next
    INDEX
    Explanations

    than digitalto firewith contractsdifficulty levelnow referred totoo quicklyRegis madeaccordingly

    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
    हमें
    0.49
    మన
    0.48
    仍然
    0.47
    訾
    0.47
    ﻦ
    0.47
    मनी
    0.47
    ༅
    0.47
    查找
    0.46
    ृह
    0.46
    ნიშვნელ
    0.45
    POSITIVE LOGITS
    robot
    0.47
     Bruder
    0.43
     Barack
    0.42
     "
    0.42
    yss
    0.40
    .
    0.40
     gyerek
    0.40
     Obama
    0.40
    bere
    0.40
    ocz
    0.39
    Activations Density 0.006%

    No Known Activations