© 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. 191407
    Prev
    Next
    INDEX
    Explanations

    plant filtration, CPU memory, perfect unison

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

    Open When... letters

    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
     Joaqu
    0.54
    拎
    0.49
     questione
    0.45
     promin
    0.45
     আদৌ
    0.44
    ocamp
    0.44
     चुनौ
    0.43
     السبب
    0.43
    mercial
    0.43
    lerini
    0.42
    POSITIVE LOGITS
     leftWheel
    0.46
    టో
    0.46
     vibration
    0.45
    สำหรับการ
    0.44
    மாய
    0.42
     carène
    0.42
    e
    0.42
    յան
    0.41
     warping
    0.41
     এইরূপ
    0.41
    Activations Density 0.001%

    No Known Activations