© 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. 196089
    Prev
    Next
    INDEX
    Explanations

    URLs and names

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

    internal buffers linked to programming

    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
     suplement
    0.53
    ্ষ
    0.50
     사라
    0.50
    макра
    0.49
    였
    0.49
     equivari
    0.49
    indexBuffer
    0.49
     харак
    0.49
     Pyongyang
    0.49
     GoObject
    0.48
    POSITIVE LOGITS
    over
    0.49
    اعد
    0.45
    ewa
    0.45
    och
    0.43
    door
    0.43
    ι
    0.41
    ear
    0.40
    Signin
    0.40
    eo
    0.40
    純
    0.40
    Activations Density 0.001%

    No Known Activations