© 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. 181905
    Prev
    Next
    INDEX
    Explanations

    jef assignEXECUTAR

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

    sometimes chaotic, call its name, like, can, peel

    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
     وص
    0.50
    后期
    0.50
    نامج
    0.46
    طلح
    0.46
     العل
    0.45
    脉
    0.45
    标题
    0.44
    PL
    0.43
     Hyun
    0.42
    措施
    0.41
    POSITIVE LOGITS
    бели
    0.52
     kilobytes
    0.50
     jef
    0.49
     craziness
    0.49
     одну
    0.47
     jednu
    0.47
     assign
    0.47
     executar
    0.47
     kayaks
    0.47
     бюд
    0.46
    Activations Density 0.000%

    No Known Activations