© 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. 45096
    Prev
    Next
    INDEX
    Explanations

    ultramarine blue

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

    regions or places

    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
     bli
    0.51
    רק
    0.51
    ELL
    0.49
    θυν
    0.47
     alten
    0.44
    缈
    0.44
    ิก
    0.44
     baat
    0.44
     cultivo
    0.44
    梂
    0.44
    POSITIVE LOGITS
    捞
    0.45
    放弃
    0.44
    နိုင်ငံ
    0.43
    coff
    0.43
    Согласно
    0.43
    一组
    0.43
    ősz
    0.42
    孟
    0.42
    ガン
    0.42
    дің
    0.42
    Activations Density 0.001%

    No Known Activations