© 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. 155211
    Prev
    Next
    INDEX
    Explanations

    step children

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

    midfielder/defender, planet, chef, cuckolding

    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
    siniz
    0.50
    佉
    0.47
    快的
    0.46
    不容易
    0.46
     necessárias
    0.45
     Dekor
    0.45
    GetLastError
    0.45
    랑
    0.45
    ٤
    0.45
    잍
    0.45
    POSITIVE LOGITS
    hv
    0.48
    hp
    0.45
    hre
    0.41
     stretching
    0.40
     climate
    0.40
     implement
    0.39
    implement
    0.39
     multimillion
    0.39
     invasions
    0.39
    aub
    0.39
    Activations Density 0.001%

    No Known Activations