© 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. 67781
    Prev
    Next
    INDEX
    Explanations

    ios apps or balloons

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

    updating model parameters

    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
    涅
    0.48
    荼
    0.47
     يتعلق
    0.47
    ᔪ
    0.47
    द
    0.46
    縝
    0.46
     그의
    0.45
    他的
    0.43
    channel
    0.43
    替え
    0.43
    POSITIVE LOGITS
     ABP
    0.52
     marinas
    0.51
     DLP
    0.49
     NPS
    0.47
     mitigated
    0.47
     Mansfield
    0.46
     হেতু
    0.46
     railroads
    0.46
     Dobson
    0.46
     schon
    0.46
    Activations Density 0.001%

    No Known Activations