© 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. 57349
    Prev
    Next
    INDEX
    Explanations

    welcome to

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

    welcome to

    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
     fyrir
    0.54
     මෙම
    0.48
    เพื่อให้
    0.46
     こちら
    0.46
    在这里
    0.46
    toLocale
    0.44
    ור
    0.44
    ൈ
    0.44
     upang
    0.44
    nCurr
    0.44
    POSITIVE LOGITS
     limbo
    0.49
     העולם
    0.48
     Uganda
    0.44
     plateau
    0.44
    j
    0.44
     Burma
    0.43
     swamps
    0.43
     hilltop
    0.42
     life
    0.41
     worlds
    0.41
    Activations Density 0.010%

    No Known Activations